Senior AI-Native Engineer

We are seeking a Senior AI-Native Engineer to design AI systems that other engineers and customers depend on, take them to production, and measure whether they work. This role operates the AI-native way: spec first, tests first, with coding agents handling implementation under review. Responsibilities Design and run production LLM systems: multi-stage pipelines or agents with a curated tool set, output schemas, validation, retries and failure recovery Build and maintain evaluation frameworks: golden datasets, regression evals on every prompt change, LLM-as-judge with spot checks, production telemetry Decide where work is autonomous, where it assists, and where a person approves Deliver spec-first and test-first with coding agents, and keep project context files (AGENTS.md, CLAUDE.md, steering files) deliberate and token-aware Integrate AI steps into CI/CD (review gates, test generation, quality hooks) and tune them against false positives Estimate AI cost before building, measure it after, and apply cost levers (model routing, context trimming, caching, batching, limits) Publish reusable skills, prompts, tool schemas, eval sets and MCP servers and keep them current Raise AI failures early and fix them structurally Help new teammates adopt the team's AI workflow Requirements At least one AI workflow or system running in production or CI without daily attention, which the candidate can explain in terms of trigger, users, own part, and how they know it works 5+ years of professional software engineering experience with production ownership 2+ years of experience building with LLMs or agents on real projects Expertise in multi-step LLM or agent design: tool restriction, output schemas, validation, fallbacks, latency trade-offs Showcase of an evaluation approach built or extended by the candidate Background in fixing wrong outputs with structural changes rather than re-runs Understanding of what drives the cost of their own AI work, with experience using at least one cost lever with a measured effect Skills in clear communication, such that a peer could rebuild their work from their description Nice to have Experience with multi-agent systems in production and brownfield discovery on a legacy codebase Familiarity with AI steps in CI/CD with measured outcomes (PR cycle time, defect density, AI acceptance rate) Proficiency in more than one model provider or platform, with reasons for each Knowledge of tracing and observability for LLM systems Experience in security-sensitive environments