Software Engineer, AI Infrastructure
Description
About the company
Our client is a software company.
The role
Raydar is recruiting for this role on behalf of our client. Design and build the backend platform that runs software-writing agents, covering how work is matched to models, how agents receive context, how their behaviour is measured, and how engineers can see what happened. The role combines production engineering with applied research aimed at making these systems better over time. Candidates should be comfortable owning open-ended problems from design through to delivery.
What you'll do
- Decide which model handles each task, weighing cost, speed and quality, and measure whether those choices were right.
- Shape what information reaches each model by designing lookup, state handling and condensing techniques, keeping only what is pertinent.
- Design evaluations that show where to improve next and whether a change made agents better.
- Build observability tools that record what each agent did, why, and at what cost.
- Use logged runs to improve the system through new tools, cheaper learned behaviour and fixes for recurring failures.
- Design how code and its history are represented, stored and versioned when agents produce much of it.
Requirements
What we're looking for
- Founder, founding engineer or similar fast-paced 0 to 1 development experience, including early-stage startup work.
- Practical familiarity with some part of agent tooling, such as choosing models for tasks, supplying information to models, judging output quality, or tracing system behaviour.
- Track record shipping large-scale AI-driven automation to real users, whether in production or internal tooling.
- Production backend or infrastructure experience, including scaling services, autoscaling, isolation and observability.
- Ability to work on-site in San Francisco, California.
Bonus points
- Academic or side-project background in program correctness, language design or model fine-tuning.
- Developer infrastructure experience, such as version control or build systems.
- Experience at a coding-agent company or on an internal coding-agent platform.
- Top undergraduate STEM degree, especially valued for less experienced candidates.
Benefits
Compensation and benefits
- Salary: $220K to $350K
- Equity
- Health, dental and vision coverage
- Flexible time off
- Retirement plan
Location and work model
- San Francisco, California, United States
- On-site, with a flexible remote option in one week of every six
- Full-time
Skills
As published by workable · 3 questions
Basics
First name, Last name, Email, Headline, Phone, Address, Photo, Education, Experience, Summary, Resume, Cover letter
Short answers (1)
- Public LinkedIn profile URL (https://www.linkedin.com/in/...)
Pick from a list (2)
- Will you require work authorization of any kind?
- Are you able to work onsite in San Francisco?
Sign in to read and join the discussion.