Senior ML Model Optimization Engineer (GPU/LLM) - Equity

Roblox; San Mateo (CA); On-site; USD 295,250 - 345,040; Full time

Benefits offered by this job

Equity compensation

Comprehensive benefits package

Job summary

Roblox in San Mateo, CA is seeking a Model Optimization Engineer to optimize machine learning models focusing on GPU performance. Candidates should have over 6 years of experience, excellent debugging skills, and proficiency in tools like CUDA and Triton. The role involves analyzing and improving performance bottlenecks while collaborating with data scientists and engineers. The annual salary range is $295,250 — $345,040 USD, with onsite requirements Tuesdays to Thursdays.

Qualifications

• 6+ years of professional experience in system design.
• Experience debugging GPUs and reading GPU profiles.
• Proficient in advanced frameworks to enhance model execution speed.

Responsibilities

• Optimize machine learning models for GPU performance.
• Conduct performance profiling analysis of machine learning pipelines.
• Collaborate with cross-functional teams on model deployment.

Skills

Debugging GPUs

CUDA

Triton

TensorRT

Model optimization techniques for LLMs

Education

Bachelor's degree in Computer Science

Job description

Roblox in San Mateo, CA is seeking a Model Optimization Engineer to optimize machine learning models focusing on GPU performance. Candidates should have over 6 years of experience, excellent debugging skills, and proficiency in tools like CUDA and Triton. The role involves analyzing and improving performance bottlenecks while collaborating with data scientists and engineers. The annual salary range is $295,250 — $345,040 USD, with onsite requirements Tuesdays to Thursdays.