Senior / Staff Machine Learning Engineer - Scene Intelligence
Core
Develop Vision-Language-Action (VLA) models to perceive robotaxi surroundings, identify hazards, and ensure safe driving in real-time.
Role type
Senior/Staff Machine Learning Engineer (VLA/VLM)
Builds
VLA solutions for robotaxis, post-training stacks for VLMs/VLAs, and data pipelines for ML flywheel
Domain
Autonomous driving, computer vision, large language models
Deliverable
production ML models
Required skills
Deep learning for VLM/VLA models, post-training (CPT, SFT, RL), production ML pipelines, dataset creation, Python (PyTorch, NumPy, Pandas, VLLM)
Preferred skills
Computer vision techniques, top-tier conference publications, LLM integration
Technologies
PyTorch, NumPy, Pandas, VLLM
Responsibilities
Design and train VLA solutions, lead end-to-end data strategy, lead full post-training stack for VLMs/VLAs, research and deploy solutions to improve driving behavior, partner with cross-functional teams to integrate perception signals
Seniority
Senior/Staff, hands-on IC
