Engineering Manager - Inference Performance

Highlights

• Lead team making demanding AI workloads run faster and more efficiently on GPUs.
• Turn performance wins into measurable tokens-per-GPU-hour and latency gains.
• Bring up and tune new model architectures on new hardware within days.

What they offer

• Meaningful equity (U.S. only)
• 100% medical, dental, and vision coverage for employee and dependents
• Flexible PTO including company-wide Winter Break
• Paid parental leave
• Fertility and family-building stipend through Carrot (U.S. only)
• Company-facilitated 401(k)

Ideal candidate

Hands-on technical leader who loves GPU performance and mentoring engineers. You thrive unblocking hard optimization problems and turning speedups into customer impact at a fast-growing startup.

Requirements

• Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or related field
• Experience managing engineers including hiring, mentoring, feedback and performance reviews
• Experience leading or supporting GPU optimization teams in training, inference or recommendation systems
• Strong technical depth in GPU workloads, architecture and performance tradeoffs
• Familiarity with ML libraries such as PyTorch, TensorRT or TensorRT-LLM
• Track record of driving roadmaps and shipping complex technical projects
• Clear written and verbal communication with ability to align cross-functional stakeholders