Systems ML Engineer: Edge & Cloud Performance

Breakout Ventures; Cambridge (MA); On-site; USD 170,000 - 260,000; Full time

Job summary

Transfyr is building physical AI for science and seeks a Systems ML Engineer to optimize and run ML models across training and production inference. You will work closely with research and perception teams to accelerate training and improve model performance on cloud and edge devices.

The role emphasizes profiling, custom kernel work, and robust deployment practices in a Cambridge, MA environment, with opportunities across levels from hands-on builders to senior leaders.

Qualifications

• Demonstrated ML systems engineering expertise deploying models in production.
• Experience profiling and optimizing large-scale training/inference.
• Ability to write custom CUDA/Triton kernels when needed.
• Cloud and edge deployment experience, with cost and security awareness.

Responsibilities

• Profile and optimize training and inference workloads across the stack.
• Develop and maintain high-performance GPU kernels (CUDA/Triton).
• Manage cloud and edge infrastructure for lab deployments.
• Collaborate with research and perception teams to improve throughput.
• Implement monitoring, versioning, and safe deployment practices.
• Debug production issues and optimize resource usage.

Skills

ML systems

Profiling

GPU kernels

Distributed training

Cloud & edge

Debugging

CUDA

Triton

Tools

Nsight

PyTorch Profiler

PyTorch Distributed

Triton

CUDA

Job description

Transfyr is building physical AI for science and seeks a Systems ML Engineer to optimize and run ML models across training and production inference. You will work closely with research and perception teams to accelerate training and improve model performance on cloud and edge devices.

The role emphasizes profiling, custom kernel work, and robust deployment practices in a Cambridge, MA environment, with opportunities across levels from hands-on builders to senior leaders.