Narvar - Sr. AI Engineer

• We care more about judgment and ownership than credentials. • judgment and ownership • You’re likely a strong fit if you: • Have shipped conversational AI or agent-based systems used by real users in production • Have built production systems on top of LLM APIs and agent frameworks — not just prompt playgrounds, but real integrations involving tool orchestration, context management, and reliability at scale • Have a point of view on model selection tradeoffs — when to use frontier APIs vs. open-weight models (Qwen, Llama, Mistral), and understand the cost, latency, privacy, and capability tradeoffs of each • Understand prompt engineering beyond basics: structured outputs, few-shot learning, chain-of-thought, tool calling • Have built context graph pipelines that go beyond naive retrieval — entity resolution, relationship modeling, and dynamic context assembly from structured and unstructured data • Have designed agent architectures that use function calling, tool execution, or multi-step reasoning • Have strong programming skills in Python or TypeScript • Have experience building and integrating APIs and backend services • Are comfortable reasoning about evaluation, safety, and reliability in non-deterministic systems • Take initiative naturally and are comfortable operating with ambiguity • These aren’t hard requirements, but strong indicators: • You’ve worked in startup or high-ownership environments • You’ve built and operated AI systems in production, including monitoring and incident response • You’ve evaluated and iterated on LLM systems for accuracy, hallucination, latency, and cost • You’ve built or integrated MCP servers or similar tool-use infrastructure • You’ve influenced technical direction by earning trust, not by mandate • You use modern tooling (including AI-assisted development workflows) to increase leverage, not outsource thinking • (Note: we care about outcome and judgment, not how flashy your tools are.)