Full Stack Software Engineer, Evaluation Tools

Overview

In this role, you will build and own fullstack features for evaluation tools used by model developers, researchers, and QA engineers to measure driving performance. You will take scenario mining from prototype to production and extend agent tooling to run end-to-end evaluation workflows. Working in the Search & Agents squad, you’ll interact with users to define success metrics and ensure reliable, scalable software that supports rapid AI driver iteration. This role offers impact at scale within a mission to advance autonomous mobility.

Pay / Benefits

• Meaningful equity
• Relocation support and visa sponsorship
• Hybrid working model
• Learning and development budgets
• Health insurance and dental
• Enhanced maternity/paternity leave

Responsibilities

• Build fullstack features across search, scenario mining, and agentic tooling
• Engage with model developers and researchers to define success metrics before implementation
• Scale the scenario mining framework to production
• Extend agent tooling for end-to-end evaluation workflows
• Work with large-scale data systems (Databricks, Spark) in an established codebase
• Own the reliability and maintainability of shipped software
• Contribute to architectural decisions that scale across products
• Leverage AI tools to improve development workflows and product quality

Key requirements

• Strong development skills in Python, TypeScript, and JavaScript with React or similar frontend framework
• Strong SQL skills with understanding of database design and optimisation
• Experience designing and building production-level fullstack systems and high-performance APIs
• Track record of building robust, maintainable systems and applying engineering best practices
• Excellent communication and collaboration across time zones
• Ability to work independently in a fast-paced, high-context environment
• Power user of AI development tools and mindset for AI-augmented workflows

• Communication
• Collaboration across time zones
• Independence in a fast-paced environment
• Python
• TypeScript
• JavaScript

…