Staff AI Engineer - Agent Architecture & Behavior

Sourced from feeny.ai

Artisan is hiring a hands-on Staff AI Engineer to design and build the core architecture for a new agentic AI product. You will own agent execution loops, multi-agent coordination, tool use, context and memory, and evaluation, taking ideas from prototype to dependable production software. This is an individual-contributor role with broad technical ownership, based in person in San Francisco.

• Design and implement agent execution loops, planning strategies, tool interfaces, and verification
• Build multi-agent delegation, coordination, context sharing, and result synthesis
• Make stateful workflows resilient with checkpoints, recovery strategies, and human intervention
• Improve retrieval, context construction, persistent state, and skill representation
• Build realistic evaluations and turn observed failures into measurable improvements
• Evaluate models and emerging techniques and make build-versus-buy decisions
• Set engineering standards and review important design decisions

• Personally built and shipped a substantial agentic system
• Deep practical experience with LLM tool use, planning, context engineering, and evaluations
• Implemented multi-agent coordination or substantial parallel agent/tool execution
• Hands-on experience with browser or computer automation in an agentic system
• Strong software engineering skills in Python, TypeScript, or a comparable language
• Comfortable with asynchronous services, state machines, persistence, concurrency, retries, and cancellation
• Ability to reason about permissions, untrusted inputs, and human approvals
• Strong technical ownership and ability to ship with urgency and care

• Agent memory and retrieval depth
• Skill acquisition or reinforcement learning / post-training
• Trajectory datasets and sandboxed execution
• Distributed systems and inference optimization
• Multimodal and voice models