Software Engineer, Model Performance Systems
Baseten · San Francisco, CA · EPD
About this role
Baseten is hiring a mid-level Software Engineer based in San Francisco, CA. The posting calls out experience with Python, LLMs, Deep Learning, Machine Learning. Compensation is listed at $160,000–$200,000 per year.
- Role
- Software Engineer
- Function
- software engineering
- Level
- mid
- Track
- Individual contributor
- Employment
- Full-time
- Location
- San Francisco, CA
- Department
- EPD
- Posted
- Jan 7, 2026
More roles at Baseten
Job description
from Baseten careersABOUT BASETEN
Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $300M Series E, backed by investors including BOND, IVP, Spark Capital, Greylock, and Conviction. Join us and help build the platform engineers turn to to ship AI products.
THE OPPORTUNITY
We are looking for early-career Software Engineers to join our team. This is a specialized role sitting at the intersection of high-performance computing (HPC) and Large Language Model (LLM) engineering. You will be responsible for building the automated "speedometer and diagnostic" suite for our next-generation AI infrastructure.
In this role, you won’t just be using models; you will be tearing them apart to see how they run on the metal. You will build tools that measure GPU FLOPS, stress-test InfiniBand clusters, and define the benchmarks that ensure our systems are production-ready.
RESPONSIBILITIES
Performance Benchmarking: Run and automate standard LLM quality benchmarks (GSM8K, MMLU) alongside custom performance suites for specific workloads (e.g., long-context window, KV cache reuse).
This is an excerpt. Read the full job description on Baseten careers →