Software Engineer, ML Inference Platform
Core
Design, build, and deploy core infrastructure components for the machine learning model life cycle, including pipelines, testing, monitoring, and deployment on self-driving robot fleets.
Role type
ML Infrastructure Engineer (Inference & Compiler Platform)
Builds
Robust and scalable ML model & data pipelines, optimized models for Nuro's fleet, and in-house ML inference and compiler platforms.
Domain
Autonomous driving / Physical AI / Distributed Systems
Deliverable
production ML models | infrastructure
Required skills
Python, C++, ML pipeline design, distributed systems, system design, data workflow orchestration
Preferred skills
C++ (high-performance), large-scale distributed systems, ML compilers
Responsibilities
Design and develop ML workflow pipelines for training, optimization, validation, and deployment; Develop and maintain continuous testing and monitoring systems for ML infrastructure; Develop observability to track ML model lifecycles; Maintain an in-house ML inference platform; Maintain an in-house ML compiler platform.
Seniority
Mid-level, hands-on IC
