Machine Learning Engineer

About the role

This position focuses on building and refining infrastructure for large language models within a growing systems engineering group. You will concentrate on hardware efficiency, distributed computing, and performance optimization to ensure AI models run effectively at scale.

Key facts

What you'll do

• Analyze and resolve performance bottlenecks within production AI environments.
• Develop benchmarking utilities to measure system effectiveness.
• Refine inference pipelines to improve overall throughput and latency.
• Scale distributed GPU setups to support high-demand workloads.
• Collaborate with research and infrastructure staff to move models into production environments.
• Maximize hardware utilization through rigorous systems engineering.

Requirements

• Degree in Electrical Engineering, Computer Science, or a related field.
• Background in building infrastructure for large-scale machine learning systems.
• Proficiency in C++ and Python, with a preference for CUDA experience.
• Familiarity with LLM serving tools like SGLang, vLLM, or PyTorch.
• Knowledge of parallel computing and GPU architecture.
• Experience with distributed inference, quantization, batching, and model serving.
• Ability to profile, debug, and optimize complex software systems.

Nice to have

• Experience managing multi-node GPU clusters.
• Familiarity with distributed computing frameworks like Ray.
• Background in high-performance computing environments.
• Skills in kernel-level or systems-level performance tuning.

Skills & tools

• Python
• C++
• CUDA
• vLLM
• SGLang
• PyTorch
• GPU architecture
• Distributed computing
• Ray

Practical notes

Benefits include comprehensive health coverage, a 401(k) plan, and unlimited PTO. The role provides access to a modern workspace and premium amenities.