AI Product Engineer

🚀 AI Product Engineer | GenAI & LLM Production Architectures | Multi-Model SaaS Platform 🌍 Remote | 📄 B2B Contract | 💰 Competitive Rate

Our client is a premier engineering and consulting partner driving ambitious platform transformations globally. This mandate focuses on moving out of the prototype phase and placing sophisticated, production-grade AI capabilities—such as automated data extraction agents, predictive platforms, and large-scale document intelligence pipelines—directly into the hands of over 9 million end users. We are seeking an authoritative engineer who builds for execution, scale, data compliance, and commercial reliability from day one.

What You’ll Be Doing:

• End-to-End AI Architecture Ownership: Own the technical lifecycle implementation for custom, multi-tenant AI features from initial source data ingestion to automated orchestration and deployment into cloud platforms.
• Agentic Workflows & Orchestration: Design flexible, modular agent configurations complete with tool-use patterns, sandboxed execution schemas, permission bounds, and human-in-the-loop checkpoints.
• RAG & Pipeline Modernization: Develop scalable document ingestion frameworks, implementing custom chunking, cross-model embeddings, vector store tuning, and hybrid search methods (vector + keyword) to assure low latency.
• Production Observability & Cost Management: Direct token budgeting at scale, per-query cost tracking, drift monitoring, and prompt template tuning to maintain stable, resilient operational infrastructure under high-traffic demands.

What We’re Looking For:

• Consultant-Grade Communication: A technical visionary with a strong product focus, capable of tracking system constraints (latency spikes, token boundaries, unpredictable inputs) and translating outcomes into clear architectural value for business stakeholders.
• Pragmatic feature design: 5+ years in professional software development paired with 2+ years of explicitly shipping real-world, compliant AI-driven services into production with minimal downtime.
• Engineering Excellence: Commitment to clean design patterns, data governance (PII handling, comprehensive audit trails), automated regression testing, and precise documentation.

Must-Haves:

• Strong backend engineering skills in at least one modern language (Python, C#/.NET, TypeScript/Node.js, Go, or Java) with framework mastery (e.g., FastAPI, ASP.NET Core, Express, or Spring Boot).
• Deep expertise with major LLM APIs (OpenAI, Anthropic) and local orchestration runtimes (Ollama, vLLM).
• Proven experience deploying vector database structures (Pinecone, Weaviate, pgvector, or OpenSearch).
• Practical knowledge of AI orchestration layers (LangChain, LangGraph, or CrewAI) and Model Context Protocol (MCP) bounds.
• Hands-on execution of data pipeline tracing and evaluation harnesses (LangSmith, Braintrust, or Ragas) integrated into cloud-native setups (AWS, Azure, or GCP).

Location & Working Setup:

• 100% Remote working model.
• US Hours overlap is possible.

If you are a senior software architect ready to scale commercial AI platforms beyond basic autocomplete loops and take complete engineering accountability, let's connect!