Engineering Manager, Inference Performance

What you'll do

• Lead, mentor, and grow inference performance engineers, including hiring, feedback, career development, and performance reviews.
• Own the runtime performance roadmap and guide profiling, optimization, and productionization of inference techniques.
• Coordinate with partner teams to ship performance improvements and measure outcomes such as latency, utilization, and cost.

What they ask for

• Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or a related field.
• Experience managing engineers, including hiring, mentoring, feedback, and performance reviews.
• Experience leading or closely supporting GPU optimization teams in training, inference, or recommendation systems.
• Strong GPU workload knowledge, familiarity with ML libraries such as PyTorch, TensorRT, or TensorRT-LLM, and a track record of delivering complex technical projects.

Nice to have

• Familiarity with inference engines such as vLLM, SGLang, or TensorRT-LLM.
• Production experience with LLM optimization, GPU kernels, rapid-growth startup teams, or hands-on performance/systems engineering.

Pay

$240K – $270K (base salary)

Tools

PyTorch, TensorRT, TensorRT-LLM, vLLM, SGLang, CUDA, Triton, CUTLASS

AI focus

Optimizes and productionizes AI inference on GPUs, including quantization, speculative decoding, KV-cache management, batching, kernels, scheduling, and support for new model architectures.