Principal Software Engineer - Data & ML Systems (Behaviors)
Description
In our Behaviors team, you have the opportunity to work with world-class Machine Learning (ML) engineers and research scientists, whose mission is to create positive social impact, by making self-driving vehicles a reality. The Behaviors team develops ML models that learn how different agents navigate complex real-world traffic scenarios. We leverage these models to set the behavior of our self-driving vehicle, and predict the behavior of other agents such as vehicles and vulnerable road users.
In particular, our large scale data pipelines are critical for efficient end-to-end ML development of our trajectory planning solutions, covering Data Caching, Imitation Learning, Reinforcement Learning-based post-training, and Open-Loop and Closed-Loop Evaluation.
We are looking for engineers who are passionate about autonomous driving, excited by intellectual challenges, and interested in pursuing career growth with a fast-moving company.
What You’ll Be Doing:
You drive project-level impact to make our autonomous vehicles operate at superhuman capabilities for comfortable, safe driving. Daily, you will:
- Architect at Scale: Lead the technical design and evolution of our data and ML pipelines, enabling massive-scale distributed training (Imitation Learning, Reinforcement Learning) and evaluation loops.
- Solve Systemic Bottlenecks: Partner directly with ML researchers to identify infrastructure friction points, designing and implementing distributed computing solutions to drastically reduce time-to-insight.
- Bridge Infrastructure and R&D: Act as the strategic technical bridge between Infrastructure and ML teams, translating technical requirements into robust, scalable software architectures.
- Drive the technical roadmap for the Behaviors ML platform, to deliver multi-quarter architectural initiatives.
- Define and enforce engineering and MLOps best practices within the Behaviors team, elevating the group's software quality and testing rigor.
- Mentor engineers for your immediate domain within the team.
What We’re Looking For:
- 10+ years of professional software engineering experience.
- BS or MS in Computer Science, Machine Learning, Applied Mathematics, Statistics, Physics or a related field; or equivalent industry experience.
- Deep understanding of ML development cycles (MLOps, ML Infrastructure, ML Platform, ML Systems).
- Familiarity with PyTorch or other deep learning frameworks.
- Experience developing large-scale ML data pipelines capable of handling complex temporal, spatial, or multi-agent datasets.
- Advanced knowledge of software architecture and engineering best practices (system design, CI/CD, rigorous testing frameworks, and SOLID principles).
- Fluency in Python, including standard scientific computing libraries and Python bindings development experience.
- Expertise in concurrency, parallel processing, and database systems (relational or non-relational).
- Experience with distributed computing frameworks (e.g. Ray, Dask or Spark).
- Experience leveraging a cloud platform (e.g., AWS or Azure) for distributed job execution and data access.
Bonus Points:
- Experience working on autonomous vehicles, or related fields.
- Strong programming skills in C++ and/or CUDA programming.
- Familiar with AI-assisted coding tools (e.g. Claude Code or Cursor).
- In-depth understanding of common Machine Learning and Deep Learning algorithms.
- PhD in Computer Science, Machine Learning, Applied Mathematics, Statistics, Physics or a related field.
Skills
Sign in to read and join the discussion.