Research Engineer, Gemini Agent Safety Post Training, DeepMind

GoogleMountain View, CaliforniaOn-siteFull-timeMid level, 2–5 yearsListed 10 hours ago

Apply now

About this role

As a Research Engineer in Gemini Agent Safety, you will architect and deploy the alignment mechanisms, sandbox behaviors, and trajectory-level training required for Gemini agents—including software engineering agents and computer-use agents—to operate safely and reliably at global scale.

This role sits within the GenAI Alignment and Safety team, the core organization responsible for safeguarding the full Gemini model family, from frontier reasoning models to deep research architectures. You will partner closely with pre-training, mid-training, post-training, and product engineering teams. As agents take on higher-stakes tasks and complex multi-step workflows, your work will directly anchor the safety foundation of Google’s AI ecosystem.

You will not only pioneer safety alignment algorithms and dynamic evaluations, but also drive the technical execution required to land these models across high-impact production surfaces.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.
We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort. Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google (https://www.google.com/about/careers/applications/benefits/).

Minimum qualifications:

- Bachelor’s degree or equivalent practical experience

- 2 years of software development or ML research experience, or education equivalent credit (e.g., internships, student research, pre-graduate working experience).

- Experience in machine learning algorithms, deep learning research, and large language modeling

Preferred qualifications:

- Experience in AI safety, alignment, and robust decision-making—including modern alignment techniques such as SFT, RLHF, RLAIF, online distillation.

- Experience training and fine-tuning large models at scale across distributed compute clusters, with familiarity in LLM serving infrastructure, telemetry logging, and continuous data flywheels.

- Experience developing or red-teaming autonomous agents in interactive sandbox environments.

- Expertise in designing and scaling automated evaluation frameworks, red-teaming pipelines, or dynamic benchmarks to identify behavioral edge cases and security vulnerabilities.

- Design, implement, and maintain high-quality protocols to identify safety gaps in model behavior across all Gemini and GenAI models, and feed these insights back into the post-training process to continuously improve both in-model and out-of-model protection.

- Explore, adapt, and apply innovative modeling and alignment techniques to solve real-world safety and alignment challenges under tight launch timelines.

- Drive innovation in model optimization, advancing the application of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques at massive scale.

- Partner closely with post-training, evaluation, and product teams to align incentives, close safety gaps, and influence safety decisions without direct authority.