As a Software Engineer on the Self-Maintaining Codebase (SMC) team, you will work on the core feedback loop that drives the intelligence, reliability, and autonomy of our next-generation coding agents.
Your mission is to build the data and evaluation flywheel for large-scale agentic software engineering: transforming execution trajectories into actionable loss analysis, pioneering automated skill improvement workflows, and hillclimbing agent success rates across complex, multi-repo codebase maintenance tasks (e.g., automated refactoring, proto optimization, dependency pruning, and Mendel flag deprecation).
Your focused areas include but are not limited to the following: AI verifier, quality hillclimbing, agent skill auto-improvement, coding agent evaluation, trajectory analysis, etc. Note this role will not focus on agent infrastructure.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $147000 - $210000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google.
Deliver innovative agentic-first solutions for a self-maintaining codebase, setting the standards for AI-driven productivity at Google.
Thrive in ambiguity by embracing rapid iterations to validate assumptions and fail fast.
Collaborate effectively with distributed teams across DE, US, and IND to define technical roadmaps, promote alignments, and oversee project execution.
Show the full description
Nurture a vibrant team environment anchored in mutual respect and relentless innovation, fostering a psychologically safe space for professional growth.
Develop a deep understanding of customer needs to balance the requirements of multiple Product Areas (PAs) and bridge the gap with the SMC offering.
Minimum qualifications
Bachelor’s degree or equivalent practical experience.
2 years of experience coding with Python.
2 years of experience working with Generative AI.
2 years of experience working with Large Language Models.
Preferred qualifications
Master's degree or PhD in Computer Science or related technical fields.
2 years of experience with Agentic AI, Evaluation, and quality hill climbing.
2 years of experience with prompt engineering; using, interacting, and evaluating AI Agents or LLMs in the coding space.
Familiarity with code maintenance, migration, and large-scale changes.
Familiarity with Google latest AI-driven coding tools.
Bachelor’s degree or equivalent practical experience.
2 years of experience coding with Python.
2 years of experience working with Generative AI.
2 years of experience working with Large Language Models.
