The role, as published
About the company
Our client is an early-stage software company.
The role
Raydar is recruiting for this role on behalf of our client. Own the design and delivery of production AI infrastructure, covering autonomous agent systems and the controls that govern them. Partner closely with technical leadership on architecture, while also taking a share of general product engineering and on-call coverage in a small, hands-on team.
What you'll do
- Lead the rebuild of core AI infrastructure so it moves from basic capabilities to a production-grade system.
- Design and implement a context-aware data layer that models relationships between people and groups.
- Build a configurable agent platform that lets end users set up their own agents and event-driven automations.
- Stand up a model-agnostic inference layer with access controls and predictable, rule-based workflow behavior.
- Contribute to full-stack product work, roughly 30% of your time, including on-call duties.
- Partner directly with the co-founders to set technical direction and raise the engineering standard.
What we're looking for
- 3+ years as a product engineer at an AI-focused startup, with a record of releasing real AI-powered products.
- Hands-on delivery of applications built on large language models, including multi-step agents, retrieval systems and evaluation tooling, with ongoing tuning of quality, speed and cost.
- Experience building domain-specific agent products and deeper agent infrastructure that goes well beyond simple wrappers.
- Background at a fast-moving startup, ideally an early-stage one.
- Strong engineering fundamentals and proficiency in TypeScript and Python.
- Bachelor's degree from a US university in a technical field such as computer science, math or physics.
- U.S. citizen, required for security clearance eligibility.
- Willingness to take on general product engineering work in an all-hands-on-deck environment.
Bonus points
- Experience building AI products for defense or government customers.
- Exposure to domain-specific AI platforms with graph-based context, multiple model providers and policy enforcement.
Location and work model
- San Francisco, CA, United States
- On-site
- Full-time
Compensation, as the posting describes it
- Equity