Performance Engineer - Inference

About the role

We are looking for a Performance Engineer, Inference to understand and improve the systems that runtimes, distributed systems, accelerators, scheduling, memory, and reliability. You will measure the system end to end, identify the highest-leverage performance gaps, and work across teams to close them while preserving correctness.

What you'll do

• Run cross-layer performance investigations across throughput, latency, memory efficiency
• Build profiling, benchmarking, and observability tools that make inference performance
• Identify bottlenecks across model servers, batching and scheduling, distributed execution, memory
• Partner with model, platform, and infrastructure teams to prioritize and land high-impact
• Validate that performance improvements preserve model quality and numerical correctness

What you need

• 2–4 yrs of experience
• Python
• Machine learning
• LLMs
• Any graduate