This vacancy is closed and no longer takes applications. See open Developer Jobs
Member of Technical Staff
- Office
- 6+ years
Salary
$200,000 - 300,000/ year
Description
You would join an AI infrastructure group that is small and focused on making large language model inference faster and more efficient.
The work spans software systems, GPU kernels and production deployments, with the goal of reliable, quick inference on many kinds of hardware.
Responsibilities
- Get new open-source models running in production, tuning them for latency and throughput.
- Improve inference serving with batching, KV caching, speculative decoding and quantization.
- Build and tune GPU kernels in CUDA, HIP and Triton across different hardware platforms.
- Set up, deploy and run heterogeneous compute clusters.
- Keep production inference systems reliable, observable and cost-efficient.
- Solve technical problems on your own, working with customers and teammates to shape solutions.
Requirements
- 1 to 6 years of software engineering work, including systems or low-level code close to hardware.
- A solid grasp of computer architecture, memory hierarchy and operating system internals.
- Experience with backend, infrastructure or systems work, plus Python and GPU tools such as CUDA or Triton.
- Experience optimizing machine learning inference or running large-scale infrastructure such as clusters or GPU fleets is valuable.
- Strong technical ownership, quick learning and sound problem-solving; customer-facing experience is useful.
- You use AI agents or coding tools to make engineering work better.
Conditions
Base salary of $200,000 to $300,000 a year.
Visa sponsorship is available.
On-site in San Francisco, California, 5 days a week.
Where you’d work
From the office, 4 or more days a week in the office
The office
San Francisco, United StatesMap for San Francisco, United States (opens in a new tab)
Visa sponsored
About the company
True Talent Solutions Partners
Office in San Francisco, United States
Also hiring in New York, United States, Boston, United States, United States and 5 more places
1 of their 26 open roles is remote
Details13 facts · Role, Location, Compensation, Employment- Tech stack
- Python
- LLMs
- CUDA
- Seniority
- Staff
- Type
- Full-time
- Specialty
- Backend
- Region
- United States
- Pay period
- Annual
Show 7 more factsShow less
- Python
- LLMs
- CUDA
Role
- Category
- Development
- Specialty
- Backend
- Seniority
- Staff
- Experience
- 6+ years
- Tech stack
- Python
- LLMs
- CUDA
Location
- Work model
- Office
- Region
- United States
- Office
- San Francisco, United States
- Days in the office
- 4 or more days
- Visa sponsorship
- Sponsored
Compensation
- Salary
- $200,000 - 300,000 / year
- Pay period
- Annual
Employment
- Type
- Full-time
Something wrong with this vacancy?
Similar vacancies
- True Talent Solutions Partners
- True Talent Solutions Partners
- Astro Mechanica
- Midstream Health
- Pinterest
- Anthropic
AV Engineer, Platform & Automation
$285,000 - 325,000 / year
- Hybrid · San Francisco, New York City
- Senior
- Sapiom
Agave- Airbyte
- Okta
Staff Software Engineer - Okta Identity Governance
$194,000 - 267,000 / year
- Hybrid · San Francisco
- Senior