Description
Posted 6 minutes ago Senior AI / LLM Engineer (RAG, OpenAI, Vector Search) Hourly: $20.00 - $25.00 Expert Est. time: 1 to 3 months, Less than 30 hrs/week We're looking for an experienced AI / LLM Engineer to design and build the first demo of M.A.R.E. XO — an AI-powered maritime intelligence assistant integrated into our existing platform. This is not a generic chatbot. The assistant must answer questions using only trusted, controlled sources such as platform data, uploaded documents, vessel information, geofence data, incident records, and exposure analytics. Responses should include citations to the original sources, minimize hallucinations, and support analyst review when needed. The scope includes designing the RAG architecture, implementing document ingestion and vector search, defining chunking and embedding strategies, creating prompt workflows, establishing AI guardrails, optimizing token usage and API costs, and collaborating with our backend/frontend team to integrate the AI layer into the existing product. We're looking for someone with strong hands-on experience building production-ready RAG systems using technologies such as OpenAI, Azure OpenAI, Anthropic, or Gemini, along with experience in embeddings, vector databases, prompt engineering, and backend integration (Node.js/TypeScript preferred). If you've built reliable AI assistants that retrieve information from structured and unstructured data with source-linked answers, we'd love to hear from you. Please share examples of similar projects, the AI stack you've used, and your recommendations for this solution. Python Node.js MongoDB TypeScript Posted 11 minutes ago AI Agent for Autonomous Reporting System Hourly: $30.00 - $40.00 Intermediate Est. time: Less than 1 month, Less than 30 hrs/week Note: This is a long term job with involvement of UAE government project. Only proposals with previus proof of work in this domain will be replied and taken forward. We are seeking a skilled freelancer to develop an AI agent for our autonomous reporting system. The project involves integrating Claude to enhance the system's capabilities and creating a user-friendly reporting dashboard. The ideal candidate will have experience in AI development and a strong understanding of reporting systems. This is a part-time engagement with a short-term duration, expected to last less than a month. AI Agent Development Artificial Intelligence Claude NodeJS Framework Supabase Python +2 Posted 1 hour ago Build an AI Agent Hourly Intermediate Est. time: Less than 1 month, Less than 30 hrs/week We are looking for an experienced AI Automation Engineer to build several AI agents and workflows using Make.com, OpenAI, and various APIs. Ansible Terraform Windows Server Microsoft Azure Technical Support Domain Migration +9 Posted 1 hour ago Vapi AI Voice Agent Developer — Build & Integrate Inbound Booking Agents (Ongoing, Per-Install) Hourly Expert Est. time: More than 6 months, Less than 30 hrs/week I run an agency that installs AI voice agents into service businesses (HVAC, roofing, and similar). I'm looking for a skilled developer to build and deploy these agents end-to-end, per install, on an ongoing basis. You'll own the full technical build for each client: Build the Voice AI agent in Vapi — natural conversation, objection handling, appointment booking. Connect the phone number (Twilio or equivalent) for inbound call handling. Ingest each client's website, services, pricing, and business info into the agent's knowledge base. Integrate with the client's CRM and calendar so booked appointments flow automatically. Build the automation layer in Make.com or Zapier to connect all the pieces. Set up Stripe usage-based (metered) billing so I'm charged/charging per booking automatically — no manual invoicing. Write and structure the agent's scripts and knowledge bank. Deliver each build as fully "set and forget" — it runs without manual intervention. You'll also build one Master Agent for my own business — a demo/booking agent that prospects call to experience the product and that books qualified calls onto my calendar. Requirements: Proven experience building and deploying Vapi voice agents (please share examples) Comfortable with Twilio, Make.com/Zapier, CRM/calendar integrations, and Stripe metered billing Able to make each agent reliable enough to run unattended Fast, communicative, detail-oriented Payment: Per install (flat rate per completed, deployed agent). Propose your per-build rate. Ongoing work — I'll have a steady flow of installs as I sign clients. The Master Agent build we'll price separately as the first project. If you can make these bulletproof and set-and-forget, this is consistent, ongoing work. Start your proposal with your favorite animal so I know you read it. Proposals without an animal in the first line will be ignored. AI Agent Development AI Bot API Twilio API Posted 1 hour ago Video Interview of AI Enthusiasts for an AI Product Fixed price Entry Level Est. budget: $20.00 Summary We're an early-stage AI startup building Hirey — an agent-to-agent marketplace that runs inside various AI tools via a plugin. Think "Upwork for AI agents": your agent finds, vets, and books the right human or agent on your behalf. We're looking for 5 AI agent enthusiasts to install our plugin (OpenClaw, Codex, Opus, Gemini), try it out, and sit for a short 10-15 minute video interview about your experience. The interview will be posted on our hirey.ai site. About 45 minutes of your time total. What you'll do Install the Hirey plugin in Codex. It connects your agent to Hirey's remote MCP server, so there's no local server, Node setup, Claude Desktop, or JSON config edit required. Setup is usually: enable the plugin, restart the AI agent you installed on. Connect to Hirey, run a sample workflow, and check out the hirey.ai page. A 10-15 minute video interview with the founding team. We'll ask about your experience with Hirey and your broader take on the AI agent/MCP ecosystem. Camera on, recorded, and published on hirey.ai — by taking part you're agreeing to be filmed and featured on our site. Who we're looking for Someone who has used AI tools in the past, especially for coding or technical tasks. You use Claude Desktop, Cursor, Codex, or similar AI dev tools regularly. Bonus: you've built or contributed to anything in the AI agent / MCP / LangChain / Claude Code ecosystem. What you get $20 flat, released via Upwork on interview completion. A feature on hirey.ai as an early voice in the AI agent space. Early access to the Hirey AI agent network if you want to keep using it. A direct line to the founding team. To apply, answer these in your proposal Have you used an AI coding tool before? Which one(s)? One sentence on a recent AI/agent project you've worked on or played with. Your timezone and earliest availability this week. Confirm you're comfortable being filmed and featured on hirey.ai. We'll respond within 24 hours and schedule interviews within 2 business days. No long applications, no portfolio review. Optimizing for speed. Artificial Intelligence Machine Learning Video Production Neural Network Posted 1 hour ago Mindstudio expert needed Hourly: $25.00 - $65.00 Expert Est. time: Less than 1 month, Less than 30 hrs/week Hi! I'm looking for someone to help me finish a MindStudio agent that I've built. It's a simple agent that uses Instagram and Google Sheets, but I'm having a few minor issues with the Google integration. I need someone who can help me troubleshoot and test the agent so that it will run smoothly in the future. - Hilde :) AI Agent Development Posted 2 hours ago AI Data Agent Engineer — Agentic Analytics Platform (Semantic Layer · NL2SQL · Evals · MCP) Hourly: $70.00 - $150.00 Expert Est. time: 1 to 3 months, Less than 30 hrs/week What we’re building We’re building an agentic analytics platform: an AI data analyst that lets business users ask questions in plain English and get trustworthy answers directly from their live data warehouse. The architecture follows the modern analytics stack: • Modern cloud data warehouse • Governed semantic layer with certified metrics, entity relationships, and business glossary • LLM agent grounded in that semantic layer • Exposed through MCP (Model Context Protocol) This isn’t a demo or research project. The platform is already live with paying customers running production workloads. We’re looking for someone who has already solved this problem in production. Someone who understands the difference between generating SQL and producing numbers a CFO will actually trust. The problem you’ll own Generating SQL with an LLM is relatively easy. Building an AI analyst that returns the same correct, governed answer every time is the hard part. That requires: • A governed semantic layer with certified metric definitions so “Revenue,” “Occupancy,” or any business metric has exactly one meaning. • Context engineering for structured data, including curated catalogs, table and column documentation, retrieval context, and keeping irrelevant information out of the model. • Retrieval that actually works using embeddings and semantic search across schema metadata, business glossaries, and previously verified queries so the agent consistently selects the correct tables and business definitions. • Eval-driven development with golden datasets, reconciliation against trusted customer reports, regression testing, answer quality metrics, freshness validation, coverage checks, and faithfulness evaluation. • Strong data engineering fundamentals including modern ELT practices, incremental pipelines, data contracts, freshness monitoring, schema drift detection, and reliable warehouse modeling. What you’ll do • Design and evolve the semantic and context layer between the warehouse and the LLM, including metric definitions, entity relationships, business glossary, and catalog curation. • Build and improve the retrieval pipeline using embeddings, vector search, and metadata RAG to ground SQL generation. • Own answer quality end to end by building reconciliation frameworks, evaluation suites, regression tests, and root cause analysis whenever a number is incorrect. • Onboard new data sources using modern ELT practices and prepare them for agent use through documentation, cataloging, governance, and quality validation. • Work alongside AI coding agents every day. Much of the platform is built agentically, and you’ll guide, review, and strengthen their output. You’re probably a great fit if you have • Built or operated a production LLM-over-structured-data system such as text-to-SQL, NL2SQL, conversational BI, semantic-layer-powered AI, or a data copilot. You can discuss real production failures and how you solved them. • Experience with several modern agentic analytics technologies, with opinions about all of them: • Databricks Unity Catalog and Genie/AI-BI • Snowflake Cortex Analyst • dbt Semantic Layer • Cube • Looker / LookML • LangChain or LlamaIndex SQL agents • Vector search (pgvector or similar) • MCP servers and tools • Expert SQL and strong Python skills. You can compare legacy reports with AI-generated SQL, identify why numbers differ, and fix the correct layer instead of masking symptoms. • Deep understanding of warehouse architecture, ELT patterns, incremental loading, data contracts, data quality testing, and medallion-style modeling. • An evaluation-first mindset. You believe in golden datasets, regression testing, LLM-as-judge where appropriate, and measuring answer quality instead of guessing. Nice to have • Healthcare or regulated data experience (HIPAA / PHI) • Cloud experience, preferably GCP (Cloud Run, Cloud SQL), although AWS or Azure is also fine • Experience reverse engineering legacy BI systems such as Power BI, DAX, or SSRS to recover business logic What this is NOT • Not a dashboard or BI developer role. The AI agent replaces dashboards. • Not prompt engineering in isolation. The engineering chal