Software Engineer (ML Inference Platform)

• The ML Infrastructure team is responsible for building & improving the core infrastructure for autonomy teams at Nuro
• In this role, you will work closely with teams across Nuro, to design, build and deploy core infrastructure components in machine learning model life cycle, to push the autonomous future forward
• You will have an opportunity to work across the full stack of machine learning solutions - from designing robust and scalable model & data pipelines to building to deploying the optimized models on Nuro’s fleet of self-driving robots!
• Design and develop ML workflow pipelines to train, optimize, validate, and deploy Nuro autonomy models
• Develop and maintain continuous testing and monitoring systems for core ML infrastructure components
• Develop observability to track ML model lifecycles from data generation to on-road validation
• Maintain an in-house ML inference platform to serve large language models efficiently
• Maintain an in-house ML compiler platform to compile, deploy, and validate Nuro autonomy models to various hardware platforms

Benefits

• Free Caltrain pass and commuter benefits
• Company stock options
• Work from home opportunities
• Health insurance

• You have a degree in BS, MS.c or Ph.D with 1+ years of relevant experience
• Domain experience: Experience working with ML pipelines; ability to understand and design complex distributed systems
• Strong proficiency in Python or similar languages. Familiarity with c++
• Technical excellence: Develop with a high standard for performance, scalability, and code quality
• Independence and productivity: Ability and willingness to dive into unfamiliar territory, learn fast, and improve complex systems
• Experience with ML compilers
• Experience with data workflow orchestration platforms
• Experience with system & framework design
• Experience working with large-scale distributed systems
• Strong proficiency in C++ or other high-performance low-level languages