San Francisco | Full-time | $180K–$250K + equity | 5 days/week in office
We’re working with an early-stage, well-funded technology company building AI-powered products for enterprise customers, and they’re looking for an AI Engineer to join the team in San Francisco.
This is a hands-on role for someone who has moved beyond AI prototypes and has actually shipped LLM-powered features to production.
You’ll be building the agents, tools, evaluation systems and infrastructure behind AI features used by real customers - with significant ownership over how those systems are designed and scaled.
What you'll do
- Build and ship LLM-powered features and agentic systems used by real customers
- Design agents that can reason, use tools and work across large datasets
- Build reliable production systems around LLMs, including structured outputs, function calling and evaluation pipelines
- Work primarily in TypeScript/Node.js and/or Python, with AWS as part of the stack
- Experiment with new approaches in agentic AI and turn promising ideas into production
- Solve the real-world problems that come with shipping AI: reliability, latency, hallucinations, evaluation and cost
- Work closely with a small, highly technical team with significant autonomy and ownership
What we're looking for
- 3–8 years of hands-on software engineering experience
- You've shipped LLM-powered features to real users in production and can talk honestly about what broke
- Strong production engineering experience with TypeScript/Node.js and/or Python
- Hands-on experience building agents or agentic systems, including LLM orchestration and tool use
- Experience with LLM evaluations, structured outputs and function calling
- You're actively following the evolution of agentic AI and have experimented beyond the standard LangChain playbook
- Bachelor's degree in Computer Science
- You're excited by early-stage environments, ambiguity and having meaningful ownership
Bonus points
- Experience working on a team with fewer than 15 engineers, or as a founding/early engineer
- Enterprise or vertical SaaS experience
- FDE, Solutions Engineering or other customer-facing engineering experience
- Anyscale Ray or similar distributed compute frameworks
- Open-source contributions in LLMs or agent tooling
- pgvector or other vector retrieval systems
- Fine-tuning or post-training experience
The opportunity
You'll be joining a small, highly technical team working at the intersection of software engineering, LLMs and agentic AI.
If you've gone beyond demos and prototypes and have put AI into the hands of real users, we'd love to hear from you.