ML Infrastructure Engineer - RDU Inference Platform, Equity

SambaNova, Inc.; Austin (TX); On-site; USD 131,000 - 197,000; Full time

Benefits offered by this job

Health insurance

HSA with employer contribution

Dental

Vision

Disability insurance

Life insurance

FSA options

One Medical

Job summary

SambaNova Systems in Austin, TX is seeking a new grad ML Infrastructure Engineer to help build the inference serving stack on our RDU accelerators. You will implement features like speculative decoding, prompt caching, and tool calling, writing production Python and integrating with vLLM and public APIs.

You will also add accuracy and regression tests to catch issues before customers. This role offers a strong foundation in ML systems and backend infrastructure within a fast-growing AI hardware

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

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

Skills

Python

PyTorch

Distributed systems

Machine Learning

LLM serving frameworks

Education

B.S. in CS/EE or related field

M.S./Ph.D. in CS/EE or related field

Tools

vLLM

SGLang

TensorRT-LLM

Job description

SambaNova Systems in Austin, TX is seeking a new grad ML Infrastructure Engineer to help build the inference serving stack on our RDU accelerators. You will implement features like speculative decoding, prompt caching, and tool calling, writing production Python and integrating with vLLM and public APIs.

You will also add accuracy and regression tests to catch issues before customers. This role offers a strong foundation in ML systems and backend infrastructure within a fast-growing AI hardware