Staff AI Engineer - Agent Architecture & Behavior
$250k - $325k • San Francisco • FullTime
Posted 1mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
Artisan is building a new, ambitious project at the frontier of agentic AI, pushing the boundaries of what AI agents can achieve. This role is for a hands-on technical lead responsible for designing and building the core AI architecture, focusing on agent behavior, multi-agent systems, tool use, context management, and evaluation. The position offers broad technical ownership as an individual contributor, involving consequential architecture decisions, writing critical system components, and close collaboration with existing engineers and leadership. The ideal candidate enjoys tackling uncertain problems and executing detailed engineering to deliver robust solutions.
Responsibilities
- Design and implement agent execution loops, planning strategies, tool interfaces, and verification mechanisms.
- Build delegation, coordination, context sharing, and result synthesis for multi-agent systems, handling concurrency, conflicts, cancellations, and stale results.
- Ensure reliable execution of complex, stateful workflows with checkpoints, recovery strategies, and human intervention points.
- Improve retrieval, context construction, persistent state, and skill representation, investigating feedback mechanisms for performance enhancement.
- Develop realistic evaluations, analyze task trajectories, and translate observed failures into measurable improvements.
- Evaluate models and emerging techniques, prototype approaches, and make informed build-versus-buy decisions.
- Set engineering standards, review design decisions, and contribute to the coherent implementation of the AI system.
- Partner with product and infrastructure engineers on production services, integrations, secure execution, and observability.
Requirements
- Proven experience building and shipping substantial agentic systems in production or rigorous open-source projects.
- Deep practical experience with LLM tool use, planning, context engineering, and evaluations.
- Experience implementing multi-agent coordination or substantial parallel agent/tool execution, including understanding failure modes.
- Hands-on experience with browser or computer automation in agentic systems, including state observation, effect verification, and failure recovery.
- Excellent software engineering skills in Python, TypeScript, or a comparable language.
- Comfort with asynchronous services, state machines, persistence, concurrency, retries, and cancellation.
- Ability to distinguish model decisions from code-enforced guarantees and reason about permissions, untrusted inputs, and external outcomes.
- Proficiency in designing experiments, debugging systems, and explaining improvements and evidence.
- Capacity for technical ownership of unclear problems, effective collaboration, and shipping with urgency and care.
Benefits
- Base salary: $250,000–$325,000 USD annually
- Equity: 0.15%–0.30%
- US visa sponsorship available