Need an experienced developer to integrate an AI-powered feature into an existing application. Small scope, fast turnaround

We are looking for a hands-on Forward Deployed AI Engineer to help build practical AI systems This is not a pure backend role and not a strategy-only consulting role. You will work close to end users, understand how their workflows actually operate, and then build AI-enabled tools that solve specific business problems. The ideal person is a strong software engineer who is comfortable with ambiguity, can communicate clearly with non-technical stakeholders, and can take an AI prototype from idea to something reliable and usable. What you will do - Learn the business workflows, systems, data, and constraints. - Build AI applications using Claude or similar large language models. - Use the right mix of prompting, retrieval, tool use, agents, and workflow automation. - Own delivery from scoping through prototype, testing, hardening, and handoff. - Create evaluations to determine whether the system is accurate, reliable, and safe enough to use. - Translate between domain experts and technical implementation. - Work carefully with sensitive or regulated data. - Document what you build so it can be maintained and reused. What we are looking for - Strong Python engineering skills. - Hands-on experience building with LLMs, preferably Claude or the Anthropic API. - Experience with RAG, structured prompting, tool use, evaluation, or agentic workflows. - Ability to operate independently in a messy, ambiguous environment. - Strong communication skills with both technical and non-technical stakeholders. - Track record of shipping working software, not just demos. - Comfort working with real-world data, integrations, and imperfect requirements. Helpful but not required - Prior forward deployed engineering, solutions engineering, or technical consulting experience. - Experience building AI tools for enterprise customers. - Experience in regulated or sensitive-data environments. - Familiarity with validation, auditability, traceability, or compliance-oriented workflows.

We are seeking an experienced Workflow Automation Specialist to design and implement a scalable email automation system that streamlines the processing of inbound requests and outbound communications for Data Subject Rights Requests. Our team currently handles a moderate-to-high volume of incoming emails from multiple sources. Much of the workflow involves repetitive administrative tasks, including reviewing emails, extracting key information, manually logging data, and sending standardized responses. We are looking for a consultant/developer who can evaluate our existing process (combination of GMail & Monday.com), recommend the best tech to use, and build a solution that significantly reduces manual effort while maintaining accuracy, visibility, and auditability (this is key!). Full job & project details in the attached PDF

ABOUT THE PROJECTS. I run a curated marketplace on Shopify (The Ever Good) and I am building out an AI automation system to handle routine tasks in the business. I am AI-savvy and have built a Python agent myself, so I understand what I am asking for. I have the architecture planned and the business requirements semi-documented for each piece. I simply do not have the time to build everything I want to build, which is why I need a developer to work alongside me. The first project is a product review collection and import system. If it goes well, there is ongoing work building out additional agents over time, one at a time. This is a potential long-term engagement depending on how the first project goes. WHAT WE ARE BUILDING. The overall system is a set of AI agents that handle specific business tasks and route outputs to a simple dashboard where I can review, approve, and trigger actions before anything goes live. The dashboard is a Lovable build that gives me a single place to monitor agent status, review outputs, and approve or return anything that needs a human decision before it moves forward. Agents are planned across several areas of the business. We will build one at a time. I will walk you through the requirements for each before you start. Examples of agents here by business category (these could change): - MARKETPLACE & CATALOG. Product Reviews (first project), Catalog Enrichment and SEO, Pricing and Margin Monitor, New Product Auto-Pricer, Maker Stories, Maker Audit, Maker Analytics, Review Monitor. - CONTENT & SOCIAL. Content Generation, Cultural Moment Monitor, Social Publishing, Pinterest Curator, Instagram DM Automation, Image Production, Founder Content Amplifier. - MARKETING & ADS. Email Sequences, Paid Media Director, Ads Performance Monitor, LinkedIn Outreach. - SEO and Search. SEO and AI Search Visibility, Crawl Error and Redirects. - THE SCHOOL (Our Coaching Offerings). AI Readiness Assessment, Coaching Prep Tool, Workshop Launcher, Course Completion Monitor, Immersion Round Tracker. - FINANCE & OPS. Profit Police, Cash Flow Forecaster, Financial Health Monitor, System Health Monitor. - CUSTOMER SERVICE & GIFTING. Customer Service Drafts, Gift Inquiry and Proposals, Basket Assembler. OUR TECH STACK (Could Change). - AI AGENT BUILDING STACK. Claude Code, Claude API, Python, Make.com, Replit, Lovable, Google Sheets API, Baserow. - OTHER BUSINESS SYSTEMS. Shopify API, DropCommerce API, Matrixify, Typeform, Stripe API, Yotpo API, Klaviyo API, Instagram Business API, Later API, Pinterest API, ManyChat API, Bannerbear API, LinkedIn API, Google Analytics 4 API, Google Search Console API, DataForSEO API, QuickBooks Online API, Google Drive API. HOW WE WORK. - HOURLY. Collaborative and iterative engagement. - REQUIREMENTS. We review together before each build and refine as we go. - QA. I handle testing and QA on my end. - DOCUMENTATION. All work is documented throughout with decision logs and handoff notes so full ownership and control remains with me at every stage. - IP. All intellectual property and work product belongs to me entirely. - CLAUDE. You are expected to maintain your own Claude environment at a level that supports serious development work with no usage limitations. - ACCESS. All business systems and APIs provided with scoped credentials as needed. - DEPLOYMENT. Production deployment is handled collaboratively. - COMMITMENT. Looking for someone who can help maintain and evolve these tools over time while I retain full control and understanding of everything we build. WHAT I AM LOOKING FOR. - CLAUDE. Must use Claude as your central AI LLM. Experience. Working experience with the Claude API and the tools in the building stack above, or a demonstrated ability to learn new tools quickly. - COMMUNICATION.Clear communicator who works independently and does not need to be managed through a task, but is promptly responsive to me. - MINDSET. Building with AI tools as a regular part of your work. TO APPLY. Please share a brief description of one or two AI agents you have built, what they did, and what tools you used. Include a note on your familiarity with the tools listed above and your hourly rate.

Looking for general help building out a platform for an AI saas.

We are seeking a senior AI developer to build and enhance AI models for our business. The role involves developing, testing, and deploying AI solutions, as well as improving existing models to increase accuracy and performance. The ideal candidate should have strong experience in AI development and be able to work independently on complex projects.

Overview We run an AI voice assistant for self-storage operators. We have an internal, AI-assisted workflow for triaging call feedback — investigating what happened on a call, diagnosing the root cause in our codebase, and drafting fixes. We’re looking for someone technical to run that AI-assisted workflow day to day and help us make it better. You’ll be driving AI coding agents, reading real code to understand behavior, and improving the process and tooling itself. What you’ll do Use our AI agent tooling to work through a queue of customer feedback on AI voice calls. Read our TypeScript/Node codebase (voice-agent prompt assembly, workflow/“SOP” engine, tool implementations) to diagnose why the agent behaved a certain way — not just guess. Draft fixes: workflow-instruction edits, knowledge-base entries, or code changes via pull request with a clear verification plan. Improve the triage process itself — refine the AI agent prompts/skills, conventions, and the internal MCP tooling that powers it. Write clear, customer-facing summaries of what changed for our team to review and approve. You’re a great fit if you Read and reason about code confidently — ideally TypeScript/Node; React a plus. Have hands-on experience driving AI coding agents (Claude Code, Cursor, or similar) and understand how LLM prompts/tools/agents fit together. Think in cause-and-effect: “the agent did X because line Y / instruction Z.” Write precisely and concisely for both technical and non-technical audiences. Are process-minded — you spot the repetitive thing and turn it into a better workflow. Bonus: prompt engineering, LLM tool/agent development, or voice/conversational AI experience. How we work We’ll start with a paid trial on a small batch, then scale steady ongoing volume. To apply: Tell us about a time you used an AI coding agent to diagnose or fix something non-trivial in a codebase you didn’t write — what you did, and how you verified it worked. A link to relevant work is a plus.

The Client seeks an experienced AI development team to design and build a secure web-based document intelligence platform capable of analyzing multiple related documents, extracting key information, identifying inconsistencies, and generating issue reports. The platform will support complex document sets where information must remain consistent across multiple files and versions. The initial scope focuses on document ingestion, data extraction, cross-document analysis, issue identification, and reporting. Business Objective Develop a scalable SaaS application that enables users to: • Upload and organize multiple related documents • Extract key terms, dates, parties, financial values, and references • Compare information across documents • Identify inconsistencies and missing information • Generate issue reports and review summaries • Maintain document version history • Provide an intuitive dashboard for issue management Phase 1 – Document Ingestion and Processing Requirements Develop a secure document upload module supporting: • PDF • Microsoft Word (.docx) • Microsoft Excel (.xlsx) • Text files System shall: • Extract text from uploaded files • Preserve document structure • Capture headings and section hierarchy • Process tables and schedules • Index document content for search and retrieval Phase 2 – Data Extraction Engine The platform shall automatically identify and extract: • Defined terms • Parties and entities • Dates • Numerical values • References to exhibits and schedules • Section references • Key metadata Extracted information shall be stored in a searchable database. Phase 3 – Cross-Document Consistency Review The platform shall compare extracted information across multiple documents and identify: • Inconsistent terminology • Conflicting dates • Conflicting numerical values • Missing references • Undefined terms • Duplicate provisions • Broken cross-references Examples include: • Same entity referenced using multiple names • Different numerical values for the same item • References to sections that do not exist • Missing exhibits or attachments Phase 4 – AI Review and Issue Identification The platform shall integrate a Large Language Model (LLM) to perform contextual analysis. The AI engine shall: • Summarize document contents • Identify potential drafting inconsistencies • Highlight missing information • Generate issue descriptions • Assign issue severity levels • Provide suggested corrective actions Phase 5 – Dashboard and Reporting Develop a web-based dashboard including: Transaction Workspace • Document list • Upload history • Processing status • Review status Issue Tracker • Issue category • Issue severity • Source document • Description • Resolution status Search Functionality Search by: • Term • Date • Party • Numerical value • Document name Reporting Generate downloadable reports in PDF and Excel format. Technical Requirements Frontend • React or Next.js Backend • Python • FastAPI preferred Database • PostgreSQL Vector Database • Pinecone, Weaviate, or Chroma AI Integration • OpenAI API • Anthropic API • Retrieval-Augmented Generation (RAG) architecture preferred Security Requirements • User authentication • Role-based permissions • Encrypted document storage • Audit logging • Secure API access Deliverables Functional web application Source code repository Database schema API documentation Deployment documentation Administrator guide User guide Ownership and Intellectual Property All work product, source code, documentation, specifications, workflows, business logic, prompts, training materials, and derivative works developed under this project shall be deemed works made for hire and shall be the sole and exclusive property of the Client. Contractor shall assign all intellectual property rights to the Client upon creation. Contractor shall not reuse, disclose, distribute, or commercialize any portion of the work product without the Client’s prior written consent.

We operate a production AI/LLM auditing platform used by a large enterprise client. This platform transcribes recordings of in-store visits completed by field representatives, then runs an LLM-driven audit schema against those transcripts to score whether specific criteria were met. The platform is live and delivering value. We're now investing in a dedicated AI specialist to push accuracy higher, expand the feature set, and bring deeper expertise to how we evaluate and iterate on our LLM pipeline. What you'll do - Build out our evaluation loop. We currently test our audit schema weekly. We want to move to more frequent, more granular testing, the full schema or individual audit questions, on demand. - Improve scoring accuracy. Our benchmark is 90%+ accuracy on most audit questions. You'll drive us there, identify the questions where 90% isn't realistic and explain why, and push a defined subset of high-priority questions well beyond 90%. - Assess the approach itself. Determine whether we need new audit schemas and questions, or whether the current approach should be refactored for better accuracy and capability. We want your judgment here, not just execution. - Ship new capabilities. -- Keyword search over transcript text, with Boolean operators, phrase search, and grouping. Returns matching snippets plus a count of transcripts containing the term. Transcripts are ASR output and imperfect, so the design needs to account for that. -- Sentiment analysis: merchant sentiment and agent sentiment across a transcript (negative / neutral / positive), plus detection of sentiment shift over the course of a conversation (e.g., a merchant who started negative and ended positive). - Evaluate emerging tooling and make recommendations we can act on. - Potentially build a schema management UI so our non-developer team can modify audit questions without engineering involvement. - Communicate frequently. We want regular written progress recaps, not silence between milestones. What we're looking for - Strong hands-on experience building and shipping LLM-powered systems in production, not just prototypes - Real depth in LLM evaluation: building eval sets, measuring accuracy against ground truth, regression testing prompts and schemas, and reasoning about where models fail and why - Prompt engineering and structured-output experience (classification, scoring, extraction) - Experience working with ASR/transcript data and its failure modes is a strong plus - Comfort with search implementation (Boolean query parsing, full-text search) is a plus - Sentiment analysis experience beyond off-the-shelf APIs - Ability to form an opinion, defend it, and communicate it clearly in writing to both technical and business stakeholders - Self-directed — you'll be trusted to identify the right problems, not just close tickets Nice to have - Experience with RAG, fine-tuning, or model selection tradeoffs at scale - Frontend capability sufficient to build an internal admin/config UI - Background in compliance, QA, or audit-adjacent domains To apply Please include: - A brief description of an LLM system you took from prototype to production, and specifically how you measured and improved its accuracy. - Your approach to building an evaluation harness for a scoring/classification task where ground truth is human-labeled. - Your availability and hourly rate. Applications that appear to be generic or AI-generated without substance will not be considered. Please reference the word "transcript" in your first sentence so we know you read this.

We are looking for 2-3 AI engineers/developers to help us build/complete an AI go-to-market (GTM) tool that looks at both structured and unstructured data, runs it all through our AI engine, and provides insights and recommendations straight to sales people. The tool is able to handle large volumes of data and provide actionable insights for business decision-making. Our engine consists of a prioritization algorithm, pattern matching and sentiment analysis. We use our recommendation engine to deliver the output (insights) straight to our tool which is "Apple-simple", intuitive and gamified. No more sales time wasted on looking at dashboards and trying to agree on which insights are important and which should be acted on. What you'll do Own features end-to-end across theFastAPI backend (IEngine) and Next.js 15 / React 19 frontend— from Claude prompt design to UI polish. Extend the intelligence pipeline: meeting ingestion (Google Drive + Deepgram realtime), Claude-driven action card generation, Neo4j relationship graph, and Supabase-backed state. Build customer-facing dashboard surfaces — deals, gamification, coaching, trust graph — with TypeScript, Tailwind, shadcn/ui, and D3. Operate WebSocket transcription sessions and async job pipelines reliably under real meeting load. Instrument with Sentry, harden auth (NextAuth :left_right_arrow: JWT :left_right_arrow: FastAPI service-to-service), and keep deploy pipelines green. Build with simulators: when you can't test against live meetings, generate realistic synthetic transcripts through our simulator service. Stack you'll work in Backend: Python 3.11, FastAPI, Uvicorn, PyJWT, Anthropic SDK, Deepgram, Neo4j, Supabase (Postgres + realtime), WebSockets Frontend: TypeScript, Next.js 15 (App Router), React 19, NextAuth 5, Tailwind, shadcn/ui, D3, Stripe Infra: Fly.io, GitHub Actions, Sentry, Supabase AI: Claude (Opus/Sonnet) for transcript analysis, action card generation, and agentic dev workflows What we're looking for 4+ years building production web applications, ideally across Python and TypeScript. Comfort designing and shipping features against an LLM API — prompt iteration, structured outputs, evals, cost/latency tradeoffs. Real Claude or OpenAI production experience required. Experience with multi-tenant SaaS patterns, JWT auth, and one or more of: graph databases, realtime systems, audio/transcription pipelines. Comfort with AI-assisted development workflows (Claude Code, Cursor, etc.) — not just as a code-completion tool, but as a way to plan and ship features. Bias toward shipping. Small surface area, high ownership, no committee.