We are seeking an experienced Automation & Integration Engineer to modernize and automate our CPA firm's operations. This role will be responsible for designing, building, and maintaining AI-driven workflows and integrations centered around CCH Axcess, Additive K-1, Microsoft 365, and other business systems. The ideal candidate combines software development, API integration, workflow automation, and AI implementation experience with deep knowledge of tax and accounting technology. This is a hands-on technical position. You will build production-grade automations, not just configure software. Responsibilities Design and develop integrations between CCH Axcess, Additive K-1, CRM, document management systems, and internal databases. Build AI-powered workflows to automate tax preparation, review, document processing, and client communication. Develop API integrations using the CCH Axcess Open Integration Platform. Automate repetitive tax workflows using APIs, webhooks, scripting, and workflow platforms. Create secure data synchronization between business applications. Build custom internal applications that improve CPA productivity. Implement OCR and AI document extraction for tax source documents. Build dashboards and reporting from tax software data. Create automation monitoring, logging, and alerting. Document all integrations and maintain technical architecture. Work directly with tax professionals to identify automation opportunities. Evaluate emerging AI tools and recommend practical implementations. Required Experience 5+ years building software integrations or business automations. Strong experience with: CCH Axcess CCH Axcess APIs REST APIs OAuth Webhooks JSON/XML Experience integrating accounting or tax software. Experience with AI APIs such as: OpenAI Anthropic Google Gemini Azure OpenAI Experience with automation platforms such as: n8n Power Automate Make Zapier Strong programming skills in one or more: Python C# JavaScript/TypeScript SQL database experience. Microsoft 365 integration experience. Git version control. Cloud experience (Azure or AWS). Preferred Qualifications Additive K-1 experience. CCH API development. CPA firm experience. Tax workflow automation. OCR and intelligent document processing. Experience with AI agents. Experience with document management systems. Power BI. SharePoint. Azure Functions or AWS Lambda. Docker. Technical Skills API Development REST OAuth JSON XML Python JavaScript SQL AI Integration Prompt Engineering Workflow Automation Microsoft Graph API SharePoint APIs Microsoft 365 Administration OCR RAG LLM Integration Git CI/CD What You'll Build Examples include: Automated K-1 ingestion into CCH. AI document classification and extraction. Tax return workflow automation. Client onboarding automation. Automated tax organizer processing. AI review assistants. Internal tax knowledge search. Automated email and task generation. Client portal integrations. Document routing. Workflow dashboards. Exception monitoring and alerts. Success Metrics Within the first 6–12 months, you will: Eliminate hundreds of hours of manual tax processing. Reduce duplicate data entry across systems. Build production-ready AI workflows. Create reusable integration frameworks. Improve tax workflow visibility through reporting and dashboards. Establish a scalable automation architecture for future growth. Nice-to-Have Certifications Microsoft Azure AI Engineer Microsoft Power Platform Developer AWS Developer Python certifications AI/LLM application development CPA technology consulting experience Ideal Background Candidates who have worked at firms or software vendors using: CCH Axcess Additive K-1 Thomson Reuters products Intuit products Wolters Kluwer tax software Tax technology consulting firms CPA firms with 100+ employees Tax automation consultancies

We’re looking for an experienced engineer or trainer to help deliver hands-on AI coding training for engineering teams. The focus is on moving engineers beyond basic Copilot/autocomplete usage into agentic workflows with tools like Claude Code, Codex, GitHub Copilot, and related tooling. Scope: Run practical workshops for engineers Teach Claude Code, Codex, and Copilot workflows Cover task scoping, prompting, reviewing diffs, and code validation Help create assets like CLAUDE.md, agents.md, slash commands, or workflow templates Advise on best practices, cost awareness, security, and team adoption Ideal candidate: Strong software engineering background Hands-on experience with Claude Code, Codex, or similar tools Experience training engineering teams Clear communicator with practical examples Please apply with relevant examples of AI coding workflows, trainings, or engineering teams you’ve supported.

I am a Ph.D. and digital product business owner who uses AI (Claude, ChatGPT, and other AI tools) every day to build, market, and scale my business. My 12-year-old son and I are looking for an experienced AI tutor who can teach us how to work with AI effectively—not just how to ask questions, but how to think, build, create, and solve problems with AI. This is an ongoing coaching relationship, not a one-time class. I already use AI daily and want to become significantly more advanced in prompt engineering, AI workflows, automation, and business applications. My son is curious, creative, and highly motivated. We want someone who can grow with him over the coming years as AI continues to evolve. WHAT WE ARE LOOKING FOR • Weekly one-on-one coaching sessions (one for me, one for my son) • Hands-on learning using real projects—not lectures or slide presentations • Practical skills that can be used immediately • A structured curriculum that builds over time • Someone who enjoys teaching and can explain complex ideas clearly • Experience with Claude, ChatGPT, and current AI tools MY LEARNING GOALS I use AI every day and want to continue improving how I work with it. Topics include: • Advanced prompt engineering • AI workflow design • Prompt refinement and iteration • Research and fact-checking • Marketing copy • Product descriptions • Sales pages • Email sequences • Business automation • AI-assisted content creation • Website content • Productivity systems • Emerging AI tools and best practices JORDAN'S LEARNING GOALS Jordan is 12 years old. While we'll certainly use AI for school projects and writing, our larger goal is to help him develop future-ready skills that will grow with him through middle school, high school, college, and beyond. We are looking for someone who can progressively teach him how to use AI to create, build, and solve problems. Topics may include: • Learning how to communicate effectively with AI and using AI to support academic success • Critical thinking and verifying AI responses • Research and creative writing • Brainstorming and problem solving • Website design and development with AI • Creating simple games with AI • Building apps and digital tools as his skills grow • Learning basic programming concepts using AI as a coach • Entrepreneurship and business ideas • Using AI to help businesses become more efficient • Marketing and content creation • Responsible and ethical use of AI • Developing confidence as a creator—not just a consumer—of AI technology The ideal tutor enjoys helping young people build real-world skills and can gradually increase the difficulty as Jordan grows. WHAT WE ARE LOOKING FOR IN YOU • Demonstrated experience teaching AI—not simply using it • Strong prompt engineering knowledge • Comfortable teaching both an adult professional and a motivated 12-year-old • Patient, engaging, and adaptable • Able to build a long-term curriculum instead of isolated lessons • Reliable, organized, and an excellent communicator Bonus experience: • Programming or software development • Website development • AI-assisted coding • Game development • Digital marketing • Entrepreneurship • Small business consulting LOGISTICS • Two weekly sessions (one for Jordan and one for me--45–60 minutes each) • Zoom • Weekly to start • Start date: ASAP • Budget: Please include your hourly rate. TO APPLY Please include: Your hourly rate. Your experience teaching AI and prompt engineering. An example of how you would structure Jordan's first month of lessons. An example of how you would structure my first month of lessons. What you think will be the most valuable AI skills for a motivated 12-year-old to develop over the next five years. Applications that do not answer these questions will not be considered. We are looking for someone who enjoys teaching, stays current with AI, and is excited about helping both a business owner and a young learner become confident, capable AI users and creators.

We are looking for an experienced API Integration Engineer to help finalize and optimize integrations for our security platform. The ideal candidate will have strong experience working with third-party APIs, authentication mechanisms, cloud-based AI services, and troubleshooting production integrations. Your primary responsibility will be to validate and configure API credentials for URL classification and IP reputation services, identify and integrate the correct Large Language Model (LLM) endpoint (OpenAI, Claude, Azure OpenAI, or custom/internal models), and ensure the overall system is secure, reliable, and high performing. This is a short-term contract with the potential for ongoing work if the engagement is successful. Responsibilities 1. Verify and configure API credentials for: - URL Classification services - IP Reputation services - Threat Intelligence APIs 2. Validate authentication methods including: - API Keys - OAuth 2.0 - Bearer Tokens - JWT 3. Identify the correct LLM provider and endpoint, including: - OpenAI - Claude (Anthropic) - Azure OpenAI - Google Gemini - Internal/custom LLM deployments 4. Confirm that all required API keys, secrets, and access tokens are correctly configured. 5. Test API connectivity and verify successful authentication. 6. Troubleshoot integration issues across development and production environments. 7. Optimize API performance, latency, retry mechanisms, and error handling. 8. Collaborate closely with our development team to resolve integration challenges. 9. Document the configuration process and provide recommendations for future maintenance. 10. Ensure best practices for credential management and secure secret storage. Required Skills 1. Strong experience integrating REST APIs 2. Experience with authentication protocols: - API Keys - OAuth2 - JWT - Bearer Tokens 3. Experience working with AI APIs including one or more of: - OpenAI - Anthropic Claude - Azure OpenAI - Google Gemini 4. Familiarity with URL reputation and threat intelligence services 5. Experience integrating IP reputation APIs 6. Strong debugging and troubleshooting skills 7. Knowledge of HTTP/HTTPS, JSON, webhooks, and API testing tools (Postman, Insomnia, etc.) 8. Experience with Python, Node.js, or similar backend technologies 9. Familiarity with cloud environments (AWS, Azure, or GCP) To Apply Please include the following in your proposal: - Brief overview of your experience with API integrations. - Examples of projects involving OpenAI, Claude, Azure OpenAI, or other LLM integrations. - Experience integrating URL classification, IP reputation, or cybersecurity APIs. - Your preferred development stack. We are looking for a highly skilled engineer who can quickly identify integration issues, ensure secure API connectivity, and help us deliver a robust, production-ready solution. If you have strong experience with API authentication, AI integrations, and troubleshooting complex systems, we'd love to hear from you.

Looking for an elite problem solver, either an ex-MBB consultant with deep technical fluency or a seasoned AI Product Manager, to act as the crucial bridge between business operations and technical AI implementation. You will be responsible for dissecting client operations, prototyping the AI logic, writing flawless engineering briefs, and driving the development team to the finish line. What You Will Do: Workflow Audits & Discovery: Lead deep-dive discovery sessions. Map out existing operational workflows, identify bottlenecks, and pinpoint high-ROI opportunities for AI automation. Prototyping & Technical Translation: Because you are an AI power user, you will prototype the initial AI prompts and logic. You will then translate your operational findings into crystal-clear engineering briefs (or PRDs) so developers know exactly what to build. Development Management: Act as the project lead during execution. Manage the engineering workstream, clear roadblocks, and ensure the final solution is delivered on time, within budget, and achieves the strategic goal. Stakeholder Alignment: Act as the primary liaison between non-technical business leaders and the technical development team. Requirements & Qualifications: Top-Tier Pedigree: 1+ years of experience at a top management consulting firm (MBB, Big 4, Tier 2) OR proven experience as a Technical/AI Product Manager. Advanced AI Fluency: You are an AI power user. You possess advanced prompt engineering skills (e.g., chain-of-thought, few-shot) and know how to force LLMs to output reliable, structured data. Elite Structured Thinking: You excel at turning highly ambiguous, messy business processes into clean, logical frameworks (using Lucidchart, Miro, etc.) and comprehensive technical requirements. Project Leadership: Proven track record of managing technical resources, tracking deliverables, managing budgets, and driving teams to a deadline.

Project Overview We are looking for an experienced AI workflow, process design, and prompt engineering expert to help us automate part of our sales and proposal development process. Currently, our project management team spends 4–12 hours developing a custom research plan and proposal for each active FSI lead. In busy weeks, we may work on 5–6 leads, which creates a significant time burden and slows down response time. We want to build a custom ChatGPT skill or AI workflow that can take sales notes, email context, and call notes, then help generate a research plan and proposal in our existing format. What We Need We need someone who can: Learn and map our current sales/proposal process Translate that process into a structured AI workflow Write effective prompts and decision trees Train or configure a custom ChatGPT skill/workflow Help the AI ask the right follow-up questions Generate proposal sections based on uploaded notes Recommend research scope, segmentation, targets, and options Output the final proposal in our existing template Desired Workflow The ideal AI workflow would allow us to upload notes from emails and sales calls. The AI would then ask a series of structured questions to determine how to write each section of the proposal. The AI should be able to: Recommend the appropriate research process Suggest project scope Identify demand segmentation opportunities Create tables for the proposal Recommend constituencies and companies to target Suggest research options Draft the proposal using our template Provide a strong first draft that our team can review and adjust Business Goal The goal is to significantly reduce the time spent developing research plans and proposals, especially for early-stage leads and marketing-generated opportunities. This is particularly important for new leads from companies we have not worked with before, where the probability of closing may be relatively low. We want to respond quickly and professionally without taking excessive time away from active client projects. Ideal Freelancer You should have experience with some or all of the following: AI workflow design Prompt engineering Custom GPTs or ChatGPT skills Sales/proposal automation Business process documentation B2B research or consulting workflows Template-based document generation AI-assisted decision trees Knowledge management or internal AI tools Experience with market research, consulting, or proposal development is a plus. Deliverables We expect the freelancer to deliver: A documented AI workflow/process map A set of structured prompts and instructions A functioning custom GPT, ChatGPT skill, or equivalent AI workflow Question logic for gathering missing proposal inputs Proposal section drafting logic Testing and refinement using sample lead notes Documentation so our team can maintain and improve the workflow Project Type This will likely begin as a one-time project, with potential for ongoing support as we refine the workflow and expand it to other proposal types. To Apply Please include: Examples of AI workflows, custom GPTs, or prompt systems you have built Your experience with proposal automation or business process automation Your recommended approach for this project Any questions you would need answered before starting

Role Overview You are the Executive AI Enablement Lead at AIVC, the person whose job is to make the executives at AIVC’s client businesses true power users of Claude, Cowork, and code- and agent-driven workflows. AIVC partners with operator businesses to drive AI-led EBITDA growth, and part of that work is bringing each company’s most senior leaders up the AI curve. You’re the person who personally designs and runs that path on every engagement: assessing where a given client executive is today; curating the right materials, videos, and course content; running 1:1 coaching; building executive playbooks; and acting as their daily operator-in-the-loop until the new workflows stick. The first concrete instance is already lined up, a named client managing partner has explicitly asked for the fastest path to becoming a power user of Claude, Cowork, and Claude Code / Skills. From there you scale: same treatment to additional client executives across the portfolio, then a documented set of executive-grade playbooks and patterns that compound across every future engagement. You are bias-toward-results – a win is the client executive’s calendar-week looking different, not a beautifully written rubric nobody uses. What You’ll Own (Outcomes) • Within 30 days of pairing with the first client managing partner, they have a working daily routine in Claude, Cowork, and Code/Skills that’s already replacing or improving how they handle at least three recurring tasks • Within the first quarter of the engagement, the client executive is a true power user — running multi-step workflows, custom Skills/Projects, and agent-assisted tasks without needing coaching scaffolding for the basics • A documented set of executive playbooks (research, writing, analysis, synthesis, workflow automation, agent-assisted tasks) that compound across every client engagement, not one-offs • A curated, current library of learning materials, videos, example workflows, and Claude-native patterns — including a clear point of view on which external courses, tutors, or expert resources are worth plugging in • Observable change in how client executive cohorts use AI: from reactive chat to repeatable, structured, outcome-oriented workflows • A foundation of training assets and patterns that scales beyond executive coaching into broader client teams in year two • A reputation among AIVC’s clients as the trusted go-to for “how do I do this better in Claude” — measured by inbound demand and engagement expansion What You’ll Do (Responsibilities) • In the first weeks: build the first client managing partner’s tailored upskilling plan — assess current usage, identify the highest-leverage workflows for their day-to-day, curate the right mix of materials / videos / course content, and recommend any tutor or expert-guided support to fold in • Provide 1:1 coaching for client executives — managing partners, founders, C-suite leaders — on Claude, Cowork, and code- and agent-based workflows • Design tailored training plans per executive that go beyond basic onboarding into advanced usage, with explicit progression from chat → workflows → agents • Curate the best external materials (videos, courses, blog posts, example projects) and rewrap them into client-ready, AIVC-flavored learning paths • Teach practical, high-leverage use cases live: research, writing, analysis, synthesis, workflow automation, and agent-assisted tasks • Help client executives move from general chat usage into repeatable workflows — Claude Projects, Skills, scheduled Cowork tasks, MCP integrations, custom agents • Serve as a real-time tutor and expert resource for client executives — over Slack, in meetings, on-site, and in async written feedback • Run office hours, workshops, and informal Q&A sessions inside client teams to keep adoption sticky between coaching sessions What We’re Looking For (Required) • Deep hands-on expertise with Claude across every surface (Claude.ai, Claude Projects, Claude Code, Claude Skills, Claude API) — and an active habit of pushing the edges of each • Strong working fluency with Claude Cowork specifically, including scheduled tasks, connected apps / MCPs, and the broader workflow surface • Strong capability with code-enabled AI workflows: you can write Python and/or TypeScript, build agents, configure MCP integrations, and ship a working internal automation end-to-end without needing an engineer • Demonstrated ability to teach non-technical but highly demanding users — you’ve made executives, founders, or senior operators meaningfully better at something complicated, not just trained engineers • Strong workflow design instinct — you can translate messy business questions into clean prompts, workflows, and systems • Polished, discreet, and effective in high-touch client executive settings — high EQ, low ego, comfortable representing AIVC inside senior client environments and around senior decision-makers • Strong bias toward practical results over theoretical AI knowledge — the metric is the client executive’s behavior change, not the elegance of the explanation • Excellent written and verbal communication; you can write a playbook a client executive will actually read and use • Comfort with significant travel to client sites and embedded, on-site engagement work • 5+ years of professional experience across some mix of: applied AI / ML, technical training and enablement, developer relations, solutions engineering, executive coaching, management consulting, or chief of staff / senior operator roles to executives Helpful If You Have (Preferred) • Prior experience coaching or supporting C-level executives, founders, or managing partners as a client-facing professional — executive coach, principal solutions engineer to executive customers, chief of staff to a CXO, or partner-level consultant • Background that combines technical depth with people skills — developer relations, solutions engineering, technical training, or learning & development at a frontier AI or developer-tools company • Direct experience building executive-facing training programs or curricula that demonstrably moved adoption inside other organizations • Hands-on familiarity with the Anthropic product surface specifically: Claude Projects, Claude Skills, Claude Code, MCP server development, Claude API • Track record of getting non-technical users to genuinely adopt a technical tool — i.e., users who chose to keep using it after the training ended • Background in management consulting, professional services, executive coaching, or learning & development — especially in environments where the customer was a senior external client • An active personal portfolio of AI work (workflows, automations, blog posts, talks, open-source contributions) you can point to • Comfort building light tooling (a Notion playbook system, a Claude Skills catalog, a small dashboard) without needing engineering support • Familiarity with AIVC’s model — operator business engagements, EBITDA-led measurement, and the broader compounding intelligence layer — or eagerness to come up the curve quickly

Eligibility: This role is open to U.S. citizens only due to client security and compliance requirements. Please apply through this posting only — do not contact Data-Sleek directly regarding this position. Applications received outside this channel will not be considered and reported to Upwork. Data-Sleek is looking for a Senior AI Solutions Engineer to lead our on-premise and government-cloud AI deployments. You will design, build, and deploy AI-powered data pipelines for clients who cannot use commercial cloud due to ITAR, CMMC, or other data residency constraints, beginning with a client in the aerospace and defense sector. Beyond this first engagement, you will become Data-Sleek's go-to engineer for AI deployments across defense and aerospace clients, building the practice rather than just executing a single project. About Data-Sleek Founded in 2020, Data‑Sleek® is a U.S.-based AI and data consulting firm that helps mid-market companies build the data foundation that AI actually runs on. We own the full path — data strategy, architecture, integration, warehousing, and AI implementation — so organizations can adopt AI with confidence, stay compliant, and scale, without first hiring an internal data team. Our distributed U.S. team (San Francisco, Los Angeles, Irvine, Dallas, Chicago, and New York) partners with clients across healthcare, finance, insurance, logistics, and technology, modernizing data platforms with best-in-class tools like Snowflake, dbt, Fivetran, Tableau, and AWS. Trusted by Fortune 500 institutions and growing companies alike, Data‑Sleek turns complex data into measurable outcomes — faster insight, lower cost, and AI projects that deliver. About the Role You will own the technical delivery of AI-powered data pipelines in restricted environments where commercial cloud is not an option. The immediate engagement centers on a Product Lifecycle Management (PLM) data migration: building a pipeline that connects to a client's SharePoint on a restricted Microsoft 365 government tenant, reads engineering documents, classifies and summarizes them, detects duplicates, and rates naming-convention compliance to produce a migration-readiness report. You will start on-premise, then help the client evaluate and move to government cloud for production. Key Responsibilities AI Pipeline Development Build AI pipelines that connect to a client's SharePoint on a government cloud tenant, read engineering documents, classify them by type, generate summaries, detect duplicates, and rate naming-convention compliance in support of PLM data migration. Catalog large document repositories and produce migration-readiness reports and Excel catalogs that give clients a clear, measurable picture of their data. Engineer document-parsing workflows across DOCX, PDF, and XLSX formats, including embedding generation and database operations. On-Premise & Government Cloud Deployment Deploy on-premise first — a Mac Mini running Gemma via Ollama — standing up, serving, and tuning local inference infrastructure. Evaluate and migrate to production on Azure OpenAI (Azure Government) or AWS Bedrock (GovCloud) when the client is ready to scale. Keep deployments compliant within ITAR-sensitive, restricted-network boundaries throughout. Architecture & Cost Advisory Produce cost models and architecture recommendations that help client IT teams make informed platform decisions based on measured data, not vendor pitches. Compare deployment options — local, Azure Government, and AWS GovCloud — on cost, performance, and compliance, and explain the trade-offs clearly. Practice Building & Delivery Serve as Data-Sleek's go-to engineer for AI deployments across defense and aerospace clients. Build a reusable capability — a repeatable AI-solutions practice — rather than executing a single one-off project. What You Bring Required U.S. Citizen: U.S. citizenship is required and non-negotiable due to ITAR and client security and compliance requirements. Production LLM deployment: You have stood up inference infrastructure — not just called an API. You've handled model loading, memory constraints, failure modes, and throughput tuning in a real deployment. Local inference: Ollama, vLLM, llama.cpp, LM Studio, or TGI. You've served open-source models (Gemma, Llama, Mistral) on local hardware. Cloud AI platforms: Azure OpenAI or AWS Bedrock — at least one. Service configuration, model access, authentication, and token-based pricing. Python: Pipeline engineering — document parsing (DOCX, PDF, XLSX), API integrations, embedding generation, and database operations (SQLite, Postgres). Experience: 5+ years post-degree in software engineering, data engineering, or ML engineering. Strong Preferences Microsoft ecosystem: Entra ID, Microsoft Graph API, and SharePoint REST API at the API level. GCC High experience is a bonus. MCP (Model Context Protocol): Experience building or consuming MCP servers — a significant plus for a fast-evolving protocol. Workflow orchestration: n8n, Temporal, Airflow, or similar. The pipeline is orchestrated, not scripted. Government cloud awareness: Understanding of what FedRAMP High, IL4/IL5, and ITAR mean for cloud architecture decisions. Embeddings & vector similarity: sentence-transformers, pgvector, Qdrant, or FAISS for duplicate detection. 
Bonus (valued if present) Aerospace or defense experience: Familiarity with ECOs, BOMs, and AS9100 saves ramp time. Apple Silicon optimization: MLX, Metal acceleration, and Ollama tuning on M-series chips. Agentic frameworks: Bedrock AgentCore or Azure AI Foundry — the future direction involves agentic AI workflows on government cloud. What This Role Is Not Model training or fine-tuning. This is deployment engineering, not research. Data science or statistical modeling. The AI here is document understanding and classification, not predictive analytics. Frontend development. The deliverable is an Excel catalog and a report, not a web app. Sales or client acquisition. Data-Sleek's leadership manages the client relationship; you focus on delivery. Engagement & Compensation Remote, US-based. Occasional on-site travel to client facilities for hardware deployment and workshops may be needed. An average of 2–3 trips for the first engagement may be possible. Compensation. $40-$55/hour Why Join Data-Sleek? At Data-Sleek, you'll lead AI deployments in environments most engineers never touch — government cloud and on-premise systems where commercial tools simply aren't an option. Your work will directly shape how defense and aerospace clients adopt AI, and you'll build a reusable capability the company grows around. We focus on doing the right thing architecturally rather than selling the most expensive option, and we give our engineers the autonomy to deliver real solutions for real constraints. How to Apply If you've shipped real LLM deployments with real constraints, we'd like to hear from you. Please submit: Your resume A brief note describing one LLM deployment you've shipped — what model, what infrastructure, what data source, and what went wrong. Data-Sleek® is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all contractors.

We're hiring a senior AI developer to build and deploy AI solutions for a fintech/credit-union platform. The work spans autonomous banking agents, fraud detection, credit scoring, and bill-pay/invoice automation — at the intersection of LLMs, cloud infrastructure, and financial-domain expertise, with security and compliance built in from the start. This is a long-term, ongoing engagement. What you'll do: AI agents & orchestration - Design, build, and deploy multi-agent systems using Amazon Bedrock Agents, LangChain, and related frameworks - Architect agentic workflows for core banking use cases: credit scoring, fraud detection, bill-pay automation, invoice management - Define agent personas, memory strategies, tool-use patterns, and escalation paths for production banking agents LLM engineering - Fine-tune, prompt-engineer, and evaluate LLMs for financial-domain tasks - Build RAG pipelines over credit-union knowledge bases, policy docs, and member data - Implement guardrails, content filtering, and compliance checks for safe, regulated outputs - Monitor performance, hallucination rates, and latency against SLAs Cloud infrastructure (AWS & Azure) - Architect and manage AI/ML workloads on AWS (Bedrock, SageMaker, Lambda, S3, IAM, VPC) and Azure (OpenAI Service, Azure ML, AKS) - Design secure, cost-optimized environments compliant with NCUA, PCI-DSS, and SOC 2 - Implement infrastructure-as-code with Terraform or AWS CDK DevOps & MLOps - Build and maintain CI/CD pipelines (GitHub Actions, Jenkins, CodePipeline, Azure DevOps) - Containerize services with Docker, orchestrate with Kubernetes (EKS/AKS) - Apply MLOps best practices: model versioning, A/B testing, canary deployments, automated rollback - Stand up observability with logging, tracing, and alerting Python development - Write clean, well-tested Python for AI pipelines, REST APIs, and data workflows - Build FastAPI/Flask microservices exposing agent capabilities to frontend and core banking systems - Integrate with financial data sources, core banking APIs, and third-party fintech services Banking applications - Build credit-scoring models using alternative data and explainable AI (XAI) - Develop real-time fraud detection with behavioral analytics, anomaly detection, and auto-decisioning - Create conversational agents for bill pay, account management, and member self-service - Automate invoice workflows: extraction, classification, approval routing, reconciliation - Partner with compliance/risk to keep AI decisions auditable, fair, and regulatory-compliant What you should have: - 5+ years software engineering; 3+ years in AI/ML or LLM engineering - 2+ years building AI for banking, credit unions, or financial services - Hands-on experience with Amazon Bedrock, LangChain, Python, AWS, and infrastructure-as-code - Working knowledge of NCUA, PCI-DSS, SOC 2, GLBA, and Fair Lending requirements - Bachelor's or Master's in Computer Science, Software Engineering, Data Science, or related field Nice to have: - AWS or Azure AI/ML certifications - Open-source LLM experience (Llama, Mistral, Phi) and self-hosted inference (vLLM, Ollama) - Vector databases (Pinecone, OpenSearch, pgvector) - Graph-based fraud networks and graph ML - AI governance / responsible AI framework experience - Prior work at a credit union, community bank, or fintech lending platform To apply, please share: - Your resume highlighting AI and banking project experience - A brief note on your most impactful AI agent or LLM project in a financial-services context - Links to GitHub, portfolio, or published papers (optional but encouraged)

## Project at a Glance - Project stage: Partially built; bootstrapped project where efficiency, speed, cost, and lean execution matter. - Expected project duration: Approximately 1 to 2 months. - Engagement type: Independent contractor / hourly engagement only. - Scale target: The app should be architected with future growth in mind, including a target capacity of 80,000+ monthly active users with reasonable headroom to scale without avoidable rework, security degradation, or performance issues. - Security posture: SOC 2 readiness should be considered from day one; certification may occur later. - Meetings: One weekly video sync of up to 60 minutes may be scheduled by mutual agreement and should be accounted for in the contractor’s proposed budget. ## Overview We are building a production-grade, multi-tenant SaaS web application designed for enterprise-level scale, security, and reliability. The application may handle employee data and is being built with SOC 2 readiness in mind from day one. This is a bootstrapped project. Speed and lean execution are critical, and every decision should balance quality with pragmatism. The product is being designed to last, scale, and withstand technical, security, and operational scrutiny. We are seeking a U.S.-based individual senior full-stack engineer who can personally lead the web app development scope through production-ready implementation, end to end. No outsourcing outside the U.S. No agencies. ## Technology Stack - Front-end: Next.js App Router, TypeScript, Tailwind CSS - Backend / API: Next.js API Routes, Supabase Edge Functions, FastAPI / Python - Database: Supabase PostgreSQL - Authentication: Supabase Auth, OAuth, SSO, MFA - Authorization: RLS / Row-Level Security, RBAC - Realtime: Supabase Realtime - LLM / AI: OpenAI / Anthropic / Gemini-compatible LLMs - Billing: Polar.sh - HRIS Integration: Unified third-party connector - Email Delivery: Resend - Analytics: PostHog - Error Monitoring: Sentry - Infrastructure: Vercel + Supabase - CI/CD: GitHub Actions - Testing: Vitest / Jest, Playwright - AI Agents: Agentic workflows, tool use, and related architecture - MCP Integrations: MCPs for ChatGPT, Claude, Gemini, or similar environments - Additional technologies may be used. ## What We Are Looking For - Experienced full-stack SaaS product engineer with a strong, verifiable portfolio - Deep expertise in Next.js and TypeScript - Production-grade Supabase experience, including RLS, Realtime, and Edge Functions - Python back-end development experience with LLM integration, including RAG pipelines, memory, or fine-tuning workflows - Experience implementing subscription lifecycle flows and seat-based access control end to end - A genuine standard for clean, well-organized, maintainable code - Demonstrated ability to design systems that can scale horizontally without structural rework - Demonstrated ability to work efficiently in a lean, bootstrapped environment - Security-first development practices, especially when handling sensitive or regulated data - Clear, prompt professional communication - Experience building AI agents or agentic workflows - Experience building MCP integrations for ChatGPT, Claude, Gemini, or similar platforms - Experience designing hierarchical multi-tenant account structures with seat-based access control ## Strongly Preferred - Hands-on experience building RAG pipelines and LLM fine-tuning workflows in production - Experience handling employee or HR data, including PII access controls, audit trails, and data residency considerations - Experience building toward SOC 2 readiness in a prior engagement - HRIS or enterprise HR system integration experience - Familiarity with OWASP, NIST CSF, or CIS Controls ## This application is being built to last and may handle sensitive employee data. We are looking for an engineer who takes code quality, data responsibility, lean execution, and long-term system health seriously. ## Please answer all 5 screening questions in your response. ## Communication - Contractor should identify normal availability windows and provide timely responses, generally within one business day during those agreed availability windows. - Day-to-day communication will generally be async through the applicable platform or contract workroom. - One weekly video sync of up to 60 minutes may be scheduled by mutual agreement for status updates, completed-work summaries, blockers, and upcoming priorities. Contractor should account for this meeting time in the proposed hourly rate or budget. - Pre-engagement sales, proposal, or introductory scoping discussions are not billable. ## Confidentiality and IP Project details are shared only after the client’s NDA is executed. If both parties decide to move forward, a separate IP Assignment Agreement is required before any offer is accepted or substantive work begins. This is an independent contractor / hourly engagement only and does not include full-time employment, salary, benefits, equity, revenue share, product ownership, or any ongoing engagement beyond the agreed scope.