AI Summary
Design, build, and scale AI agent systems for production use. Collaborate with infra, frontend, and product teams. Develop multi-step pipelines, tool-using agents, and robust memory systems.
Key Highlights
Build, refine, and scale AI agent systems
Collaborate with infra, frontend, and product teams
Develop multi-step pipelines, tool-using agents, and robust memory systems
Technical Skills Required
Benefits & Perks
Full-time, in-person role in San Francisco (Presidio)
O-1 visa sponsorship for exceptional candidates
Relocation assistance
Job Description
The position
- Please read first
- This is a full-time, in-person role based in San Francisco (Presidio) - we work from the office 5 days a week .
- You must be based in the Bay Area or willing to relocate before starting .
- We require US work authorization , but are open to O-1 visa sponsorship for truly exceptional candidates.
- As an Applied AI Engineer , you'll be responsible for building, refining, and scaling the agent systems inside the company from architecture to evals to deployment.
- This isn't a research role. We care about what works in production: fast response times, predictable behavior, traceability, and uptime.
- You'll work across the stack with infra, frontend, and product to make sure the agents users build inside the company are robust, useful, and usable.
- Implement multi-step, tool-using agents that hit real APIs and handle retries, auth, timeouts, and edge cases.
- Build RAG pipelines that support grounded answers from structured and unstructured sources.
- Design agent memory systems that persist relevant state across runs e.g., scratchpads, summary buffers, embedding stores.
- Add determinism + replay to agents so users can trace and debug behaviors step by step.
- Own and evolve our eval framework both automated checks and human-in-the-loop scoring.
- ${your ideas}.
- 3 to 7 years minimum experience in AI in similar roles
- Previous work experience: either in an early-stage start-up (small team, high autonomy, fast pace)either in a recognized Big Tech company ( Meta, Google, AWS, etc. )
- Fluent professional English (working language in San Francisco)
- Availability to work on-site in San Francisco, 5 days/week
- Opening of an O-1 visa (exceptional talent) Company fully sponsors it
- Having already delivered complex products or contributed to open source projects
- 3+ years of engineering experience, including time shipping production software.
- Experience building and deploying agent-like systems multi-step LLM pipelines, tool-using bots, scripted assistants, or similar.
- Hands-on experience with RAG pipelines, agent memory systems, tool use and orchestration, and evaluation.
- Ability to write production-grade code and work across systems without needing a spec.
- Thrives in fast-paced, product-first environments where the goal is shipping.
- Bonus: Experience with frameworks like LangChain, CrewAI, or DSPy, shipped agents live in the wild, familiarity with LLM ops, tracing, observability, and failure handling, and experience as a founder or early engineer.
- Experience with multi-step LLM pipelines, tool-using bots, scripted assistants.
- Hands-on experience with RAG pipelines, agent memory systems, tool use and orchestration, and evaluation.
- Experience with frameworks like LangChain, CrewAI, or DSPy.
- Familiarity with LLM ops, tracing, observability, and failure handling.
- Application
- 15-min intro call: Quick check to align on location, motivation, and logistics.
- 45-minute technical interview: Build a small full-stack app.
- System design interview: Deep dive into how you think and architect systems.
- Final conversation: Quick vibe check, answer your questions, and scope out the work trial.
- Work trial: Paid, in-person, and real typically 3 days to 2 weeks.
- Full-time, in-person role based in San Francisco (Presidio) with work from the office 5 days a week.
- Open to O-1 visa sponsorship for truly exceptional candidates.