Staff AI Engineer, Agentic AI Harness & Quality - Moveworks
Core
Building and maintaining high-performing compound AI systems, specifically agentic AI harnesses, evaluation frameworks, and quality assurance for customer-facing enterprise assistants.
Role type
Staff AI Engineer (Agentic AI & Quality)
Builds
Production-grade agentic AI platforms, evaluation benchmarks, and automated harness optimization tools for enterprise workflows.
Domain
Enterprise AI / Agentic AI / LLM Operations
Deliverable
production ML models
Required skills
Compound AI system engineering, LLM and agent evaluation fundamentals, Python, Golang, API contract design, data quality for eval datasets, generative UI, dynamic agent orchestration, multimodal I/O, reasoning strategies, grounding and verifiability, deployment safety, automatic harness optimization.
Preferred skills
Experience with frontier LLMs, reading and building on AI research, critical reading for agent instruction bugs, Mac development environment proficiency.
Technologies
Python, Golang, Frontier LLMs, Mac development environment
Responsibilities
Design and maintain high-performing compound AI systems; drive quality in agent behavior and success rates; create eval benchmarks and context engineering solutions; research and develop scalable solutions for hard AI problems; partner with platform teams to deliver user experiences; optimize agent cognitive architecture and orchestration.
Seniority
Staff, hands-on IC with strategic impact
