About the company
Our client is a technology company.
The role
Raydar is recruiting for this role on behalf of our client. Work on low-level performance and infrastructure engineering for a production machine learning serving platform. You will tune software for speed and efficiency, run large compute clusters, and speak directly with customers as part of a small, high-ownership team.
What you'll do
- Deliver fast support for newly released open-source models, tuned for low latency and high throughput.
- Improve the model serving stack with techniques such as request batching, caching, decoding strategies and quantization.
- Write and tune low-level GPU kernels across several hardware vendors.
- Design, deploy and operate compute clusters built from mixed hardware.
- Run production inference across a varied fleet, with attention to reliability, observability and cost efficiency at scale.
- Talk with customers and help set the direction of your own work with a high degree of autonomy.
Requirements
What we're looking for
- Deep understanding of how computers work, including architecture, memory hierarchy and operating system internals, beyond application-level coding.
- Backend, infrastructure or systems experience at a well-regarded technology company or an early-stage startup.
- Real enthusiasm for using AI agents and coding tools to improve your own workflow.
- A computer science degree from a strong undergraduate program.
- Clear communication and emotional intelligence, as roughly 10 to 20 percent of the role is customer-facing.
- Comfort working on-site five days a week.
Bonus points
- Experience deploying or operating infrastructure at scale, such as clusters or large GPU fleets.
- Experience with machine learning inference optimization.
- Familiarity with GPU programming.
- Academic background in low-level systems topics.
- New graduates with strong internships are welcome.
Benefits
Compensation and benefits
- Base salary: USD 200,000 to 300,000 per year
- Equity
- Health, dental and vision coverage
- Meals provided
- Unlimited paid time off
- Parental leave
Location and work model
- San Francisco, CA, United States
- On-site, 5 days per week in office
- Full-time
Skills Required
- Deep understanding of computer architecture, memory hierarchy, and operating system internals
- Backend, infrastructure, or systems experience at a technology company or early-stage startup
- Enthusiasm for using AI agents and coding tools to improve workflow
- Computer science degree from a strong undergraduate program
- Clear communication and emotional intelligence
- Willingness to work on-site five days per week
- Experience deploying or operating infrastructure at scale, including clusters or large GPU fleets
- Experience with machine learning inference optimization
- Familiarity with GPU programming
- Academic background in low-level systems topics
- Strong internships for new graduates
What We Do
Raydar is a talent acquisition and business consulting firm that connects world-class and emerging talent with growing organizations. It supports companies through team development, strategic hiring, and customized growth solutions, helping clients recruit roles such as engineers, product managers, executives, legal counsel, and quantitative traders. Raydar focuses on understanding each organization’s needs, culture, and long-term goals to build high-impact teams.
