CareerPlanSign in

Software Engineer, ML Performance Optimization

Foster City, CA💼 Full-time🗓 2026-05-28 → 2026-09-26

Core

Design, implement, and operate ML training and inference performance optimization techniques to scale VLM, VLA, and Foundational models for autonomous robotaxis.

Role type

Senior IC ML Performance Optimization Engineer

Builds

Scalable ML training and inference systems for autonomous driving

Domain

Autonomous driving / Robotics / Large-scale ML

Deliverable

production ML models

Required skills

Large-scale model training/inference platform experience, PyTorch, GPU-accelerated inference (TensorRT), Profiling tools (Nsight, PyTorch Profiler), Python, C++

Preferred skills

Distributed training, Quantization, Distillation, Pruning, SOTA accelerators

Technologies

PyTorch, TensorRT, NVIDIA Nsight, C++, Python

Responsibilities

Design and implement ML performance optimization techniques; Collaborate with cross-functional teams on architectural decisions

Seniority

Senior, hands-on IC

Sourced via lever · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.