5 hours ago
Base Salary
$250k - $325k/yr
Responsibilities
- Design and implement agent execution loops, planning strategies, tool interfaces, verification, and clear system boundaries.
- Build multi-agent delegation, coordination, context sharing, result synthesis, concurrency handling, cancellation, and stale-result management.
- Make stateful workflows resilient through checkpoints, recovery strategies, partial-failure handling, and human intervention.
- Improve retrieval, context construction, persistent state, memory, and reusable skill representation.
- Build evaluations and experiments, analyze task trajectories, and measure quality, reliability, latency, and cost improvements.
- Evaluate models and emerging techniques and make informed build-versus-buy and tooling decisions.
- Set engineering standards, review important design decisions, and maintain ownership of the AI architecture and shipped results.
- Partner with product and infrastructure engineers on production services, integrations, secure execution, and observability.
Requirements
- Personally built and shipped a substantial agentic system through production use or rigorous, reproducible open-source work.
- Deep practical experience with LLM tool use, planning, context engineering, evaluations, and multi-agent or parallel agent/tool execution.
- Hands-on experience with browser or computer automation in an agentic system, including state observation, effect verification, and failure recovery.
- Strong software engineering ability in Python, TypeScript, or a comparable language, including asynchronous services, state machines, persistence, concurrency, retries, and cancellation.
- Ability to distinguish model decisions from guarantees enforced in code and reason about permissions, untrusted inputs, uncertain outcomes, and human approvals.
- Ability to design experiments, debug real system behavior, explain measured improvements, and take ownership of ambiguous problems.
- Useful additional experience includes agent memory and retrieval, skill acquisition, reinforcement learning or post-training, trajectory datasets, sandboxed execution, distributed systems, inference optimization, and multimodal or voice models.
- No specific degree, publication record, previous employer, or agent framework is required.
Benefits
- Full-time role based in person at the San Francisco office.
- US visa sponsorship is available.
- Equity of 0.15%–0.30% is offered.
- Small team, short feedback cycles, direct communication, high standards, and substantial freedom to explore ambitious technical ideas.
Tech Stack
Categories
About Artisan
Artisan builds an AI-driven outbound sales platform that functions as an autonomous BDR for B2B teams, handling prospect discovery, personalized outreach, reply management, and meeting booking. The privately held company is headquartered in San Francisco and sells its product as a SaaS platform that consolidates multiple sales tools. Reported customers include CookUnity, SaaStr, and Quora.