The role, as published
About the company
Our client is a fast-growing software company.
The role
Raydar is recruiting for this role on behalf of our client. Build and maintain production AI agents, pipelines and services, and strengthen the infrastructure used to run, test and watch them. The role pairs closely with product and security colleagues to bring language model capabilities into dependable features.
What you'll do
- Build and maintain scalable AI agent systems, data pipelines and backend services.
- Create tooling for running, evaluating and monitoring AI agents.
- Partner with product and security colleagues to design and ship AI-driven features.
- Track progress in large language models and agent techniques and adopt those that improve the product.
What we're looking for
- At least a year of hands-on work creating autonomous software that runs on language models.
- Experience coming from a company with a strong engineering bar, such as a large technology firm or a well-regarded AI software business.
- Solid software engineering background building reliable production systems.
- Experience building and deploying applications that use large language models.
- Working knowledge of the tools engineers use to write and ship code, such as version control hosts, build pipelines and editor plugins.
Bonus points
- Prior work with business software vendors or a fast-moving young company would be a plus.
- Background creating agents that work with files or write code would be a plus.
- Experience with TypeScript and React.
Benefits
- Medical, dental and vision coverage
- Flexible spending accounts for health and dependent care
- Commuter benefits
- Unlimited paid time off
- 401(k) retirement plan
Location and work model
- San Francisco, CA, United States
- On-site
- 5 days a week in office
- Full-time
Compensation, as the posting describes it
- Equity