Senior Software Engineer, Evaluation Infrastructure

About the role

Waabi is a leader in Physical AI, building autonomous trucks and robotaxis. The Evaluation Algorithms team creates the tools and algorithms needed to assess the performance of its autonomy system across development stages. This role works closely with systems, safety, and simulation teams to deliver robust evaluation capabilities.

Key responsibilities

• Develop tooling, infrastructure, and pipelines for complex statistical analyses of driving performance at scale.
• Implement metrics and tags to provide holistic model performance insight and enable discovery of interesting scenarios for training and evaluation.
• Build and maintain a high‑availability query service for low‑latency analysis over large volumes of metric and tag data.
• Work with large datasets from real‑world driving and Waabi World, the high‑fidelity simulator.
• Champion engineering excellence by writing high‑quality, well‑structured, and well‑tested code.
• Assist in project roadmap planning, prioritisation, and delivery.

Required profile

• MS or Bachelors degree with 2+ years of industry experience in Computer Science, Machine Learning, or a related technical field.
• Proficient in Python programming with strong software‑engineering fundamentals.
• Open‑minded, collaborative team player willing to help others.
• Passionate about self‑driving technologies and solving hard problems.

Required skills

• Python
• Data processing pipelines
• ETL pipelines
• Distributed computing
• Building highly reliable and scalable web services
• Cloud job orchestration
• Monitoring and instrumentation best practices
• Evaluating complex ML models or self‑driving software stacks