Staff AI Engineer - Agent Architecture & Behavior
About the role
Hands-on technical lead role focused on designing and building the underlying AI architecture for agentic systems, multi-agent coordination, tool use, context handling, and evaluation. Individual-contributor with broad technical ownership operating in a San Francisco office.
Responsibilities
- Agent architecture and behavior. Design and implement agent execution loops, planning strategies, tool interfaces, and verification. Turn ambiguous technical requirements into clear system boundaries and working code.
- Multi-agent systems. Build delegation, coordination, context sharing, and result synthesis. Handle concurrent work, conflicting updates, cancellation, and stale results. Establish when a multi-agent approach improves on a simpler baseline.
- Reliable execution. Make complex, stateful workflows resilient to interruptions and partial failures. Build checkpoints, recovery strategies, and appropriate human intervention into the architecture.
- Context, memory, and reusable methods. Improve retrieval, context construction, persistent state, and skill representation. Investigate how systems can use feedback and prior experience to perform better without introducing regressions.
- Evaluation and experimentation. Build realistic evaluations, analyze task trajectories, and turn observed failures into measurable improvements. Compare approaches using quality, reliability, latency, and cost.
- Model and tooling decisions. Evaluate models and emerging techniques, prototype promising approaches, and make informed build-versus-buy decisions. Choose tools because they solve the problem, and be willing to replace them when the evidence changes.
- Technical leadership. Set engineering standards, review important design decisions, and help the team implement a coherent AI system. Stay close to the product and accountable for what ships.
Qualifications
- Personally built and shipped a substantial agentic system. Production use or rigorous, reproducible open-source work matters more than the name of a framework or employer.
- Deep practical experience with LLM tool use, planning, context engineering, and evaluations. Implemented multi-agent coordination or substantial parallel agent/tool execution and can explain failure modes.
- Hands-on experience with browser or computer automation in an agentic system, including observing state, verifying effects, and recovering from failures.
- Excellent software engineering skills in Python, TypeScript, or a comparable language. Comfortable with asynchronous services, state machines, persistence, concurrency, retries, and cancellation.
- Ability to discern which decisions belong to a model versus guarantees enforced in code. Reason carefully about permissions, untrusted inputs, uncertain external outcomes, and human approvals.
- Ability to design meaningful experiments, debug real system behavior, and explain improvements and remaining evidence gaps.
- Willingness to take technical ownership of unclear problems, collaborate with other engineers, and ship with urgency and care.
- Depth in at least a few areas such as agent memory and retrieval, reinforcement learning or post-training, trajectory datasets, sandboxed execution, distributed systems, inference optimization, or multimodal/voice models.
Skills
About Artisan
AI employees called Artisans, starting with an AI BDR
At Artisan, we’re building real AI employees - not copilots, not assistants, but autonomous teammates. Our first, Ava, is an AI BDR. She finds and researches leads, writes emails in customers’ tone of voice, runs outbound sequences, self-optimizes, and manages email deliverability infrastructure. She learns, adapts, and improves over time - just like a human would. Human team members use Artisan as their primary working platform, replacing a sprawling stack of sales tools, and have Artisans working alongside them. We went through Y Combinator (W24) and have raised $35M+ from top investors. We’re at $6M+ ARR, with hundreds of customers including Remote, Quora, and SumUp. We’re currently working on Ava 2.0, pushing the boundaries of what an AI employee can do. And we're hiring.
More open roles at Artisan
- Builder1mo agoSan Francisco, New York · Engineering
- Staff AI Engineer - Agent Architecture & Behavior1mo agoSan Francisco · Engineering
- Founding Growth Marketer1mo agoSan Francisco · Marketing
- Founding Growth Marketer1mo agoHybrid (San Francisco) · Marketing
- Forward Deployed GTM Architect2mo agoSan Francisco, New York · Forward Deployment