AI Product Engineer

We build products where AI is the core capability. Our AI Product Engineers work on client engagements across the US and Europe, shipping LLM-powered features, retrieval systems, agentic workflows, and AI-native applications into production.Recent projects include: an AI agent that extracts structured settlement data from unstructured financial documents with 95%+ accuracy, full audit trails, and multi-tenant deployment for enterprise clients; an AI clinical platform that reduced prescription validation from 20 minutes to 5 minutes across 47 healthcare centers, built and maintained by a 5-person team; and a revenue optimization platform that processes booking data across thousands of facilities using multi-provider LLM orchestration, vector search at scale, and document intelligence pipelines.These are not demos. They handle real data, real users, real compliance requirements, and real consequences when they break. If that is the kind of work you want to do, keep reading.WHAT YOU WILL DODesign and implement AI-powered features end-to-end, from architecture through deployment and ongoing monitoring. On a typical engagement, you will:Build RAG pipelines: document ingestion, chunking strategy selection, embedding generation, vector store integration, retrieval evaluation, and re-ranking. One recent system processes unstructured emails, PDFs, Excel files, and images into structured data for a financial services platform with regulatory audit requirements.Integrate LLM APIs into production applications with structured output, function calling, and multi-model routing. Manage the tradeoffs between accuracy, latency, and cost that only matter when real users are waiting.Develop agentic workflows with tool use, human-in-the-loop checkpoints, and multi-agent coordination. A recent healthcare engagement uses LangChain-based agents with MCP endpoints to orchestrate clinical document routing across multiple systems while maintaining data governance.Build evaluation infrastructure: automated test sets with known-correct answers, field-level accuracy metrics, regression detection in CI/CD, and production monitoring that catches degradation before users doDesign human-in-the-loop workflows where low-confidence AI outputs route to expert reviewers, and reviewer corrections feed back into the systemOwn production operations for AI features: latency optimization, cost management, drift monitoring, and incident response for non-deterministic systemsSKILLS & EXPERIENCE4+ years in software engineering with at least 2 years building AI-powered features or products in production.Languages & FrameworksPython (primary), TypeScript/Node.jsAt least one web framework: FastAPI, Flask, Django, Express, or Next.jsFamiliarity with async patterns, streaming responses (SSE/WebSocket), and batch processingLLM & AI SystemsLLM APIs: OpenAI, Anthropic, open-source models (Ollama, vLLM, or similar)Prompt engineering at a systems level: structured output, chain-of-thought, few-shot patterns, function calling, tool useMulti-model architectures: routing between models, tiering by cost and complexity, fallback chainsFine-tuning pipelines and when fine-tuning is the right approach vs. RAG or prompt engineeringRAG & RetrievalVector databases: Pinecone, Weaviate, pgvector, Chroma, OpenSearch, or equivalentEmbedding models, chunking strategies (fixed, semantic, sentence-based), and the tradeoffs between themHybrid search (vector + keyword/BM25), re-ranking, and retrieval evaluation methodologyDocument processing: OCR pipelines (Azure Document Intelligence or equivalent), multi-format handling (PDF, Excel, CSV, email, images)Agent Frameworks & OrchestrationLangChain, LangGraph, CrewAI, Autogen, or equivalentMCP (Model Context Protocol) for multi-agent coordinationCustom orchestration engines: when frameworks add value and when direct API calls are simplerTool use patterns: sandboxed execution, scoped permissions, action approval gatesEvaluation & ObservabilityEvaluation frameworks: LangSmith, Braintrust, Ragas, or custom eval harnessesProduction monitoring: output quality tracking, latency, cost per query, model drift detectionTracing for multi-step AI pipelines (input/output/latency/tokens at each step)Human-in-the-loop feedback loops and confidence-based routingInfrastructure & ProductionContainerization and cloud deployment (AWS, Azure, or GCP)CI/CD for AI systems, including automated evaluation runsData pipeline design (Snowflake, dbt, or equivalent data transformation tooling is a plus)Latency optimization: streaming, caching, async processing, token budgetingCost management at scale: per-query cost tracking, model tiering, response cachingData governance: PII handling, audit trails, compliance in regulated environmentsWHAT SETS YOU APARTYou can walk us through an AI feature you shipped to production and tell us what went wrong. When you talk about RAG, you talk about chunking tradeoffs and retrieval accuracy, not just that you used a vector database. You have dealt with latency at scale, cost surprises, inputs the model was not trained for, and explaining AI behavior to stakeholders who care about results, not architecture. You build evaluation into your systems from day one because you learned what happens when you do not.What’s in it for youWork your way — anywhere, anytime. Our remote-first approach lets you choose where and how you work best!Experience working with diverse teams and gaining international expertiseA friendly, supportive team and an enjoyable work environment where your ideas matterA chance to work on exciting, challenging projects using cutting-edge technologies that make a real impactComprehensive health insurance, corporate psychologist access, and partial sports activity coverageFree training programs, reimbursement for certifications, and access to online learning platforms to fuel your growthPaid vacation, public holidays, and sick leave are fully covered by Forte GroupReferral bonuses, regular performance reviews, and full support for business tripsCorporate events and holiday presentsAbout Forte GroupFounded over 25 years ago, Forte Group began with a focus on Quality Assurance and has since evolved into a dynamic force in the tech industry, delivering cutting-edge solutions worldwide. As an American company headquartered in Boca Raton, USA, we've had the privilege of partnering with over 400 clients, including Fortune 500 giants. Our software has made a significant impact, reaching more than 9 million users — comparable to the entire population of New York or Switzerland!We’re more than just a company — we’re a team of passionate, driven people who love what we do. If you’re looking for a place where your work matters, your ideas are valued, and your growth is supported, you’ve found it!Check out the vacancy below and send us your CV. We can’t wait to meet you!By applying for the position, you consent to the processing of your personal data by Forte Group, including affiliated branches, for recruitment purposes. For more information on how we handle your data and your rights under GDPR, please review our Privacy Notice