Ai Harness Engineer

Experteer Overview In this role, you will architect and build agentic AI systems embedded in real lab workflows, collaborating with domain SMEs to deliver safe, governable automation.You will shape how agents, RAG, and orchestration patterns operate within a registry-driven platform, ensuring governance, traceability, and measurable production readiness.You’ll work closely with cross-functional teams to ship reusable assets and elevate the pod’s capabilities in a regulated environment.This is a hands-on, edge-engineering position with impact on scalable AI-enabled lab workflows.Compensaciones / Beneficios * Define the pod’s architectural approach for agents, RAG, and orchestration, aligned with reference patterns * Build and integrate skills as minimal, independent capabilities within the registry and ensure MCP/A2A spine compatibility * Embed quality, eval, and observability from sprint 1 via the shared eval harness and production-ready gates * Maintain risk-tier compliance and human-in-the-loop commit points for regulated use cases * Contribute platform assets (skills, patterns, eval sets) back to the registry for reuse * Coach rotating domain SMEs and practitioners to sustain AI solution usage and feedback to core platform Responsabilidades * Full-stack engineering experience with production-grade LLM applications * Experience building agents, RAG, evaluation, observability, and deployment * Familiarity with MCP or similar tools and registry-based system design * Comfort operating in a regulated environment with audit trails * Strong communication skills capable of demos and cross-disciplinary collaboration * Curiosity about AI, its potential and pitfalls, plus a track record of continuous learning and reinvention * Bachelor’s or Master’s Degree or equivalent * 8+ years of relevant experience (level-appropriate) Requisitos principales *

Compensaciones / Beneficios * Define the pod’s architectural approach for agents, RAG, and orchestration, aligned with reference patterns * Build and integrate skills as minimal, independent capabilities within the registry and ensure MCP/A2A spine compatibility * Embed quality, eval, and observability from sprint 1 via the shared eval harness and production-ready gates * Maintain risk-tier compliance and human-in-the-loop commit points for regulated use cases * Contribute platform assets (skills, patterns, eval sets) back to the registry for reuse * Coach rotating domain SMEs and practitioners to sustain AI solution usage and feedback to core platform Responsabilidades * Full-stack engineering experience with production-grade LLM applications * Experience building agents, RAG, evaluation, observability, and deployment * Familiarity with MCP or similar tools and registry-based system design * Comfort operating in a regulated environment with audit trails * Strong communication skills capable of demos and cross-disciplinary collaboration * Curiosity about AI, its potential and pitfalls, plus a track record of continuous learning and reinvention * Bachelor’s or Master’s Degree or equivalent * 8+ years of relevant experience (level-appropriate) Requisitos principales *