Reinforcement Learning jobs

Snapshot

• Build the infrastructure and datasets that teach Gemini to code by curating the world's largest collection of executable environments & challenges.
• The Bolt team is the owner of the largest dataset of executable environments for model training and evaluation. We are expanding our coverage of real-world code repositories to mine tasks for reinforcement learning and other LLM post-training activities.

About Us

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

The Role

Key responsibilities:

• Participate in the full SDLC of a software system including Apache Beam data pipelines, GitHub Actions workflows, security sandboxes, application-level proxies, Internet protocols, storage, and compute.
• Integrate, maintain and enhance third party open source software to work within Google infrastructure.
• Work with researchers and cross teams to prioritize technical work and deliver required data.
• Delve into a variety of popular package managers, programming languages, application frameworks and libraries to produce build recipes for code repositories.
• Curate and / or automatically build evaluation sets, devise and run ML experiments to hillclimb coding performance based on the environments that are built by the team.
• Produce training datasets of diverse tasks, run ablations to prove datasets' effectiveness, upstream datasets to OneRecipe.

About You

In order to set you up for success as a SWE at Google DeepMind, we look for the following skills and experience:

Requirements:

• Proficiency in system programming languages such as C / C++, Golang.
• Readability in Python, Golang, C++.
• Experience with running ML experiments.

In addition, the following would be an advantage:

• Systematic thinker and engineer who find joy in traversing the full stack from kernel to application in widely varied environments in order to debug issues.
• Positive, gritty technologist who can overcome ambiguity and pressure to deliver what is sought by users in a short time frame.
• Rigorous and meticulous analyst who will want nothing but the best datasets they can curate.
• Generalist who has experience in open source software used in Google.

The US base salary range for this full-time position is between 141,000 USD - 202,000 USD + bonus + equity + benefits. Your recruiter can share more about the specific salary range for your targeted location during the hiring process.

Application deadline: January 31, 2026

Note: In the event your application is successful and an offer of employment is made to you, any offer of employment will be conditional on the results of a background check, performed by a third party acting on our behalf. For more information on how we handle your data, please see our Applicant and Candidate Privacy Policy

At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.