Job Description
A company that is building the semantic layer that makes enterprise data trustworthy for AI agents is looking for an AI Engineer. Small founding team, design partners live, your work ships.
The role
Own the AI systems at the core of the company — agents, LLM workflows, evaluations — turning natural language into reliable answers over real enterprise data.
And it's bigger than the product. At this company, AI is how they operate — marketing, sales, product, CS, engineering all run on agents and workflows that the team built. We want someone who'll help build an AI-powered company, not just an AI product.
What you'll do
Ship LLM-based agents and workflows to production. Own prompting, context, evals, and answer quality. Work with data and product on how the semantic graph feeds the agents. Build internal AI tooling that makes every team faster — core to the role, not a side project.
What we're looking for
- 2+ years shipping AI products to production (not prototypes)
- Strong engineering fundamentals — you write code that holds up, you ship
- Strong Python, comfortable with Docker and Git
- You live and breathe AI: daily Claude Code user, build your own skills and subagents, write evals as a reflex, opinions on agent architectures
- AI enabler mindset — you see workflows everywhere and ask "why isn't an agent doing this?"
- Founding-team temperament: ownership, speed, ambiguity
Nice to have
Background in data, analytics, or semantic layers. Experience designing multi-agent systems or LLM eval frameworks.
