Latency Optimization Jobs

About the role We are looking for a Software Engineer with deep experience in optimizing the application-layer software

deployment on a variety of embedded compute platforms Develop compute usage strategies to optimize efficiency and latency of model inference for

Construct Pareto frontiers across model quality, latency, throughput, memory footprint, communication, and compute cost.

The optimization target here is not tail latency on a vehicle - it is throughput, cluster goodput, and cost per unit of data processed.

Kernel optimization, compiler performance, runtime scheduling or distributed accelerator systems.

Track critical serving metrics including Time-to-First-Token (TTFT), Inter-Token Latency (ITL), request throughput, tail latency (P99), and capacity efficiency.

Profile and optimize time to first token, request throughput, tokens per second per GPU, tail latency, GPU utilization, memory efficiency, and rack-level

Develop visuomotor policies for grasping, in-hand manipulation, and whole-arm manipulation, with reliable, low-latency execution on hardware.

bandwidth and latency while minimizing congestion, pauses, pause spreading, unfairness, etc.

Requirements will not arrive as a finished bandwidth and latency specification.

latency while minimizing congestion, pauses, pause spreading, unfairness, etc.

maintain cloud-based OTA infrastructure leveraging distributed systems, containerization with Docker, and orchestration frameworks to support high-volume, low-latency

Monitor network and system performance — uptime, latency, bandwidth utilization, and capacity — across all sites; proactively detect and resolve

These systems require careful data modeling, reliable integrations, and thoughtful tradeoffs across correctness, latency, scale, and cost.

Strong skills in debugging, performance optimization, and data analysis; exceptional analytical skills and engineering fundamentals.