Senior GPU Machine Learning Engineer

Lead GPU code optimization and model acceleration remotely from Canada or the UK as a full-time Senior Machine Learning Engineer. Improve efficiency at high request volume.

Raydar is recruiting for a software company client needing senior-level experience comparable to large technology company engineering. This position focuses on profiling GPU hardware, accelerating models, and deploying reliable inference systems. Relevant work includes C++, CUDA, Rust, optimized Python, and inference frameworks.

Key Responsibilities:

• Profile code for efficient GPU hardware use
• Tune model serving performance and throughput
• Move models from research into production
• Use weight compression and model knowledge transfer
• Apply token prediction, batching, and caching

Requirements:

• Senior-level experience developing software for real users
• Hands-on inference optimization framework experience
• Systems programming proficiency in relevant languages
• Familiarity with high-concurrency distributed systems
• Experience with container orchestration

Bring senior machine learning engineering experience to GPU optimization, model acceleration, and dependable production inference systems.