Machine Learning Infrastructure Engineer

About this role

TRM Labs is seeking a Machine Learning Infrastructure Engineer to help develop a robust GPU-backed infrastructure that supports AI systems for detecting financial crime. The role involves optimizing high-throughput ML workloads, managing distributed inference strategies, and ensuring seamless collaboration across various engineering teams.

What you'll do

• Design and manage GPU cluster infrastructure
• Optimize high-throughput inference systems
• Implement distributed inference strategies
• Enhance model optimization workflows
• Schedule and manage heterogeneous workloads
• Build observability for ML infrastructure

What they're looking for

• Experience with distributed systems
• ML/LLM inference on GPU clusters
• Understanding of high-throughput inference
• Familiarity with ML serving frameworks
• Kubernetes or orchestration systems
• Ability to debug GPU-related issues
• Adaptability and autonomy
• Strong communication skills

Benefits

• Impactful work in crime prevention
• Collaborative team environment
• Opportunity to leverage cutting-edge technology
• Mission-driven organization
• Diverse and inclusive workplace
• [unknown]