New Grad ML Infra Engineer — RDU Inference & APIs

SambaNova, Inc.; San Jose (CA); Vor Ort; USD 131.000 - 197.000; Vollzeit

Benefits dieser Stelle

Health insurance

HSA

Dental

Vision

Disability insurance

Life insurance

FSA

Headspace

Gympass+

One Medical

EAP

Zusammenfassung

SambaNova is building an end-to-end AI inference stack on the RDU accelerator. The ML Infrastructure team maintains the serving stack, APIs, and testing to ensure fast and reliable model delivery in production.

As a new grad ML Infrastructure Engineer in San Jose, you will write production Python for the inference stack, adapt vLLM and related frameworks, and contribute tests to ensure accuracy and performance before customers deploy.

Qualifikationen

• BS 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.

Aufgaben

• 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.

Kenntnisse

Python programming

Algorithms & data structures

Distributed systems concepts

Machine learning basics

Concurrency & systems design

Ausbildung

BS in Computer Science, Electrical Engineering, or related field

Tools

vLLM

SGLang

TensorRT-LLM

PyTorch

Jobbeschreibung

SambaNova is building an end-to-end AI inference stack on the RDU accelerator. The ML Infrastructure team maintains the serving stack, APIs, and testing to ensure fast and reliable model delivery in production.

As a new grad ML Infrastructure Engineer in San Jose, you will write production Python for the inference stack, adapt vLLM and related frameworks, and contribute tests to ensure accuracy and performance before customers deploy.