I need a full-stack developer to build a simple AI-powered chat assistant. The app should allow users to type a question and receive a response from the ChatGPT API. The UI should be clean, responsive, and built with React and TypeScript. Main Requirements: - Build a simple React + TypeScript frontend - Add a chat input and response area - Connect the app to the ChatGPT/OpenAI API - Show loading state while the AI is responding - Handle basic API errors - Keep the code clean and easy to understand - Provide short setup instructions in a README file

We are looking for an AI Consultant who can help train our team on how to use Claude effectively for project management, task organization, workflows, and productivity. Responsibilities include: • Training the team on how to use Claude for daily tasks • Helping create project management workflows using AI • Teaching the team how to organize projects, tasks, follow-ups, and SOPs • Showing us how to use Claude to save time and improve communication • Helping build simple systems the team can actually follow • Supporting leadership with AI tools for better delegation and accountability Requirements: • Strong experience using Claude and AI tools • Experience with project management systems and workflows • Ability to train a team clearly and patiently • Very organized and process-driven • Must be able to simplify AI so the team can use it daily • Experience with Asana, Slack, or similar tools is a plus We are looking for someone who can help us implement AI into our operations and train the team from A to Z.

We are looking for an experienced AI trainer / speaker to deliver a 2–3 hour live, remote Introduction to AI training session for a B2B field sales team The audience will be group of sales professionals. The client is in the protective packaging and packaging automation industry. Their sales team works with customers on packaging materials, packaging processes, damage reduction, labor efficiency, sustainability, throughput, and automation-related opportunities. The goal of the session is to provide a practical and engaging introduction to AI usage in sales workflows. This should not be a highly technical AI course. The focus should be on helping sales professionals understand how AI can support their daily work and improve sales productivity. Desired session focus: Practical introduction to AI and generative AI for non-technical sales users How field sales teams can use AI safely and effectively AI for account research and customer meeting preparation AI for improving discovery questions and understanding customer pain points AI for writing better follow-up emails, summaries, and sales messaging AI for preparing customer-specific value propositions AI use cases relevant to B2B consultative sales Responsible AI use, including confidentiality, accuracy, and human review Live examples and practical demonstrations The ideal trainer should be able to make the session engaging, practical, and relevant to a sales audience. Experience training sales teams, B2B commercial teams, or business users on AI adoption is strongly preferred. Experience in manufacturing, packaging, industrial sales, logistics, automation, supply chain, or similar B2B industries would be a strong plus, but is not mandatory if the trainer can tailor examples appropriately. Trainer responsibilities: Prepare and deliver a 2 hour session Tailor examples to a B2B field sales audience Include practical AI demonstrations that sales professionals can relate to Explain AI concepts in simple business language Provide guidance on safe and responsible use of AI tools Keep the session interactive and engaging for the group Coordinate with us in advance to align the session with client goals Ideal candidate qualifications: Strong experience delivering AI, generative AI, or digital productivity training Comfortable presenting to business and sales audiences Ability to explain AI concepts without unnecessary technical complexity Strong communication and facilitation skills Experience with tools such as ChatGPT, Microsoft Copilot, Claude, Gemini, or similar AI platforms Ability to tailor training examples to client-specific business scenarios Prior experience with sales enablement, B2B sales workflows, or customer-facing teams is preferred Please include the following in your response: Brief summary of your AI training experience Examples of similar business or sales-focused AI sessions you have delivered Your approach for making a 2–3 hour AI session practical and engaging Any relevant industry experience with B2B sales, manufacturing, packaging, logistics, supply chain, or automation Your availability in August for this training session

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.

EroFlow Intelligence is an enterprise-grade, autonomous AI orchestration pipeline designed to mitigate global supply chain disruptions for aerospace manufacturing. Built using a multi-agent framework, the system automates the entire lifecycle of risk detection, impact analysis, and procurement mitigation without requiring human intervention for standard operational anomalies. The architecture coordinates three specialized, asynchronous AI agents that communicate via a centralized event bus to solve complex logistical bottlenecks in real-time. Core Agent Architecture & Workflow 1. The Sentinel Agent (Data Ingestion & Extraction) Role: Continuous Global Monitoring. Function: Utilizes advanced LLM-driven web scraping and unstructured data extraction to monitor global news feeds, geopolitical shifts, weather anomalies, and shipping port telemetry. Trigger: If it detects a disruption (e.g., a port strike or critical mineral shortage), it extracts key entities (materials affected, estimated delay times) and passes a structured JSON payload to the orchestration layer. 2. The Impact Assessment Agent (Predictive Modeling) Role: Deep Cross-Referencing & Analytics. Function: Upon receiving a trigger, this agent cross-references the disrupted material with the company’s internal ERP (Enterprise Resource Planning) database and current inventory levels. Output: It runs a predictive analysis to determine exactly which production lines will stall and calculates the financial risk, assigning a high/medium/low priority score to the event. 3. The Mitigation & Logistics Agent (Autonomous Execution) Role: Operational Resolution. Function: If the risk score exceeds a specific threshold, this agent is authorized to take action. It autonomously queries pre-vetted alternative suppliers via APIs, negotiates standard volume pricing based on historical contract data, drafts a comprehensive procurement proposal, and queues the purchase order for final human sign-off (or executes it automatically if under a certain dollar cap). Technical Stack (The Blueprint) Frameworks: LangGraph / CrewAI (for multi-agent state management and deterministic routing). Core Language: Python 3.11+ Data Layer: PostgreSQL (for ERP syncing) & Pinecone / Qdrant (Vector database for storing and querying supplier contract PDFs and historical compliance documentation). LLM Orchestration: OpenAI GPT-4o / Anthropic Claude 3.5 Sonnet utilized via structured outputs (Pydantic parsing) to ensure strict API data integrity. Hosting & DevOps: Containerized via Docker, orchestrated via Kubernetes, and deployed on AWS with asynchronous task queues managed by Celery and Redis. Quantifiable Business Results (The Hook) 92% Reduction in supply chain anomaly response time (from 48 hours down to 14 minutes). Automated Recovery: Successfully mitigated over 140 potential production line stalls autonomously in simulated stress tests. Cost Efficiency: Saved an estimated $1.2M in expedited shipping fees by predicting bottlenecks 10 days before they impacted manufacturing floors.

Overview I have a Next.js website with a newsletter signup form that currently submits directly from the browser to HubSpot's Forms v3 endpoint. I want to add a lightweight LLM-based spam filter that inspects each submission *before* it reaches HubSpot, and silently rejects (or flags) anything that looks like spam/bot/junk input. Current setup - Framework: Next.js (App Router, TypeScript, React client component) - The form component (`NewsletterForm.tsx`) POSTs directly to `https://api.hsforms.com/submissions/v3/integration/submit/[portalId]/[formGuid]` - Fields collected: `firstname`, `lastname` (optional), `jobtitle`, `email` - Portal ID and Form GUID are public form identifiers (no secrets today) What I want you to build 1. Create a server-side API route in the Next.js app (e.g. `app/api/subscribe/route.ts`) that: - Receives the form fields from the client - Runs an LLM spam/quality check (e.g. OpenAI or similar) to classify the submission as legit vs. spam — checking for gibberish names, fake/disposable emails, nonsense job titles, injection attempts, etc. - If legit → forwards the submission to HubSpot (server-side) - If spam → rejects gracefully with a generic message (no HubSpot write) 2. Update the existing `NewsletterForm.tsx` to POST to the new internal API route instead of calling HubSpot directly. 3. Keep the LLM API key server-side only (use an environment variable — never expose it to the client). 4. Preserve the existing UX: loading / success / error states should still work. Deliverables - Working API route with the LLM spam check + HubSpot forwarding - Updated form component - Brief note on which env vars to set (`OPENAI_API_KEY`, etc.) and how to configure them - Clean, typed TypeScript that matches the existing code style Nice to have (optional) - Basic rate limiting / honeypot field as a cheap first line of defense before the LLM call - Configurable spam threshold or a logged "reason" when something is rejected Requirements to apply - Strong Next.js App Router + TypeScript experience - Experience calling an LLM API (OpenAI or equivalent) from a server route - Familiarity with HubSpot Forms API is a plus To apply, please briefly answer: 1. Which LLM/provider would you use and roughly what would it cost per submission? 2. How would you handle the case where the LLM API is slow or down — do you fail open (let it through) or fail closed (block it)? 3. Have you integrated with HubSpot Forms before? (yes/no is fine)

We're hiring a senior engineer for a focused proof of concept. Full details shared with shortlisted candidates. THE PROJECT Prove, within 4-8 weeks, that an open-weight base model adapted with a curated sample of our proprietary data produces measurable improvement on culturally specific tasks: local references, language nuance, culturally appropriate responses instead of generic default answers. At the final review, stakeholders run agreed prompts against the base model and the adapted model side by side and see where our data improved the output. This is a feasibility sprint, not production work. Potential follow-on work if it goes well. DELIVERABLES The full list below is due within the 4-week window, with a progress review at the midpoint and a final review at the end. Sequencing is yours to propose; you are the expert. What is fixed is the complete list: - Written base model selection and benchmarking recommendation against our tasks and data-sovereignty constraints. - A controlled, reproducible environment for inference and adaptation (versioned configs, run tracking). - Curated data sample and a clean held-out evaluation set. - Evaluation framework v0 that scores base vs adapted outputs across agreed domains, with baseline results established before adaptation. - Adaptation experiment (LoRA/QLoRA/SFT/distillation as the data dictates and licenses permit) with a quantified before-and-after against the held-out set. - A single-language multilingual proof of concept. - Demo-ready V0 supporting the side-by-side comparison on agreed prompts. - Initial governance, safety, and provenance framework. - TPU/GPU deployment assessment. - Integration spec for our agent and routing layer. Phase 2 roadmap. - Full handover package: source code, configs, adaptation scripts, prepared datasets, evaluation and architecture documentation. CONSTRAINTS - All work runs inside our controlled environment. No company data touches any third-party or externally hosted inference service. Compute is provided; you tell us what to provision. Open-weight licenses must permit commercial use. OUT OF SCOPE Production deployment and MLOps, full-scale training runs, ingestion of the full corpus, broad domain and language coverage, and any guaranteed quality numbers. We report what the evals show. REQUIREMENTS - Hands-on experience fine-tuning open-weight LLMs (not just API fine-tuning), building evaluation harnesses with held-out sets, and working with data that cannot leave a controlled environment. - Experience with multilingual or non-English model evaluation is a strong plus. You personally lead and stay hands-on; a small support team is fine but the core work is not delegated. TO APPLY, answer these directly (applications that skip them are ignored): - Describe the largest open-weight fine-tuning project you have personally executed: model, technique, dataset size, and what measurable improvement you achieved. - How would you build an evaluation framework for subjective cultural quality, where "better" is not a benchmark score? Be specific about held-out sets, judges, and gold standards. - Have you deployed or assessed deployment on TPUs as well as GPUs? Describe. - Given the full deliverables list above, how would you sequence the 4 weeks? Brief outline is fine; we want your plan, not ours. Can you start soon, and can you commit the full 4-weeks without competing obligations?

About the Role Assembly Software is a B2B SaaS company serving law firm customers and is actively expanding its internal AI capabilities. We are seeking a highly skilled AI contractor to serve as our embedded AI program lead — someone who can own and advance the design, implementation, and governance of AI tooling across the entire organization. This is a hands-on, strategic role. You will work directly with IT leadership and cross-functional teams to assess our current AI landscape, close gaps, and build a mature, secure, and operationally excellent AI program. We are a heavy Anthropic/Claude shop. Strong familiarity with Claude, the Anthropic API, and the Model Context Protocol (MCP) ecosystem is a significant advantage for this role. Core Responsibilities • Audit existing AI tool usage and identify overlaps, gaps, and shadow IT • Design and implement a company-wide AI governance framework • Lead MCP server setup, integration, and lifecycle management • Configure and manage Claude Teams/Enterprise deployments • Build and maintain an internal AI Skill Library for staff use • Define AI security policies and data access controls • Evaluate and recommend new AI tools and vendors • Establish prompt engineering standards and best practices • Connect AI tooling to internal business systems (Salesforce, M365, Asana, and others) • Support AI integrations with sensitive data sources including our data warehouse and CRM • Produce documentation, SOPs, and executive-ready reporting • Train internal staff and stakeholders on AI capabilities and safe usage Required Qualifications • Hands-on AI implementation experience in enterprise environments • Deep familiarity with large language model platforms, particularly Anthropic Claude and OpenAI • Proven experience building and managing MCP (Model Context Protocol) servers and integrations • Strong understanding of AI security — data exposure risks, access scoping, governance controls, and audit logging • Experience integrating AI tooling with business systems such as Salesforce, Microsoft 365, or similar platforms • Ability to author clear governance documentation, security policies, and executive-facing deliverables • Comfortable operating independently with minimal oversight while maintaining strong stakeholder communication Preferred Qualifications • Hands-on experience with the Anthropic Claude API, including system prompt design, tool use, and agentic workflows • Background in B2B SaaS, legal technology, or other regulated industries • Familiarity with SOC 2 compliance requirements as they relate to AI tooling and data access • Prior experience standing up internal AI assistants or Copilot-style tooling connected to live business data • Knowledge of data warehousing and secure query patterns for LLM-to-database integrations • Familiarity with CI/CD workflows and lightweight DevOps for deploying AI services

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

**** Agencies are welcome to apply, but put your GenAI solutions architect on the very first interview call. Not a salesperson who then hands off **** We are an AWS partner company focussed solely on Data & AI implementation work. We are specifically looking for a GenAI Solutions Architect to lead pre-sales engagements with customers. Typical duties include: 1/ Executing pre-sales discovery calls with customers 2/ Demoing our proprietary production GenAI demo environments and mapping customer use-cases 3/ Performing deep GenAI assessments and helping provide roadmap for implementation and planning 4/ Compile Statement of Work for customer projects We have a number of tools that will assist in this process to ensure compliance with our patterns and standards. The ideal candidate should have at least 3 yrs of hands on GenAI implementations, understanding of RAG, MCP, bedrock, agentcore experience, strands/langchain experience, and the ability to clearly understand business needs and articulate/map out to technical implementations. Our interview process is unique since this is a LONG running engagement: Step 1: Interview with a technical executive Step 2: Interview with a Sr. technical engineer Step 3: After NDA is signed, train on one of our IP environment (5 hr commitment from your side, but likely faster if you are already familiar with GenAI & AWS) Step 4: Present to a panel on the concept. This is where we evaluate your ability to present what you have learned and earn trust, similar to how you would be doing customer facing.