ML Infrastructure Engineer - New Grad
About the Team
The ML Infrastructure team builds and operates the inference stack that serves SambaNova's models on our RDU accelerators. We cover request scheduling, caching, decoding techniques, public APIs, and the accuracy testing that every inference feature must pass before it ships.
About the Role
As a new grad ML Infrastructure Engineer, you'll write production Python for our inference serving stack, including our vLLM integration and public APIs. You'll help bring features like speculative decoding, prompt caching, and tool calling into production on the RDU, and add accuracy and regression tests that catch problems before customers do.
Responsibilities
Implement inference features on the RDU such as speculative decoding, constrained decoding, tool calling, prompt caching, and long-context inference
Adapt vLLM and related serving frameworks to the RDU architecture
Build and maintain endpoints in the public inference API
Write accuracy verification and regression tests for inference features
Debug latency, throughput, and reliability issues in production services
Required Qualifications
B.S. in Computer Science, Electrical Engineering, or related field
Strong programming skills in Python
Understanding of algorithms, data structures, concurrency, and systems design
Coursework or project experience in distributed systems or machine learning
Experience with LLM serving frameworks such as vLLM, SGLang, or TensorRT-LLM
Experience with inference techniques such as speculative decoding, KV caching, or continuous batching
Experience with PyTorch
Preferred Qualifications
M.S. or Ph.D. in Computer Science, Electrical Engineering, or related field
Experience building or maintaining APIs or backend services
Internship or research experience in ML systems or backend infrastructure
Experience with disaggregated systems - prefill/decode
Open source project ownership or contributions
Base Salary Range:
Base Pay Range
$131,200—$196,800 USD