Senior Software Engineer, ML Infrastructure
Core
Design and build scalable data pipelines, distributed training infrastructure, and MLOps systems to turn raw autonomous driving data into high-quality training sets and reliable model releases.
Role type
Senior/Staff ML Infrastructure Engineer
Builds
Scalable data pipelines, distributed training/evaluation infrastructure, and MLOps tooling for autonomous driving models
Domain
Autonomous freight / Machine Learning Infrastructure
Deliverable
production ML models
Required skills
Python, PyTorch, Ray (Core/Data/Train/Tune), distributed training (DDP/FSDP), SQL, pandas, statistics, experimental design
Preferred skills
GPU cluster management, job orchestration, multi-tenant environments, model serving
Technologies
PyTorch, PyTorch Lightning, Ray, SQL, pandas
Responsibilities
Design reproducible data pipelines for scenario discovery and labeling; curate balanced training/evaluation datasets; build distributed training and evaluation pipelines on GPU clusters; implement MLOps practices (artifact management, experiment tracking, automated testing); define and validate model metrics; develop dashboards for result visualization; partner on GPU scheduling and compute cost optimization; lead technical strategy and mentor engineers
Seniority
Senior/Staff, hands-on IC with technical direction
