Machine Learning Inference Engineer

Oscar Technology; San Francisco (CA); Hybrid; USD 225,000 - 275,000; Full time

Benefits offered by this job

Equity

401k matching

Medical coverage

Competitive base salary

Job summary

Oscar Associates Limited (US) in San Francisco offers a hybrid Senior ML Inference Engineer role. You will enhance AI-native infrastructure powering generative and multimodal models, with ownership across inference systems and production performance.

The ideal candidate has 3+ years of experience, strong Python and PyTorch skills, and familiarity with GPU tooling like Triton, TensorRT, and vLLM. Equity and full benefits accompany a competitive base salary.

Qualifications

• 3+ years of professional ML experience required.
• Strong understanding of GPU infrastructure for AI-native systems.
• Hands-on with Python and PyTorch; building model-serving microservices.

Responsibilities

• Improve efficiency of AI-native infrastructure for generative and multimodal models.
• Own inference systems and production model performance.
• Collaborate across teams to optimize deployment.
• Experience with diffusion and multimodal models is a plus.

Skills

GPU infra

Python

PyTorch

Triton

TensorRT

vLLM

Diffusion

Model-serving

Multimodal models

Tools

Triton

TensorRT

Job description

Title: ML Inference Engineer

Location: San Francisco, CA

Salary: $250k base + equity

An AI Unicorn startup is hiring a Senior Machine Learning Inference Engineer for a full-time role.

You will be responsible for improving efficiency for AI-native infrastructure powered by generative and multimodal models. The ideal candidate has over 3 years of professional experience and a strong understanding of GPU infrastructure, Python, and PyTorch. This is a highly autonomous role with significant ownership across inference systems and model performance in production.

This role is hybrid in San Francisco Bay Area and offers full benefits and equity.

Experience:

• Building AI applications at scale from the ground up

• Strong understanding of GPU infrastructure including Triton, TensorRT, or vLLM frameworks

Hands-on experience with Python and PyTorch

• Building model-serving Microservices

• Diffusion and Multimodal model experience is a plus

Benefits:

• Competitive base salary

• Equity

• $401k matching

• Medical coverage

Oscar Associates Limited (US) is acting as an Employment Agency in relation to this vacancy.