Research Engineer, Multimodal Reinforcement Learning job opportunity at DeepMind.

Home Jobs In Switzerland Tag: Frontier AI Research Engineer, Multimodal Reinforcement Learning position at DeepMind


bot
DeepMind Research Engineer, Multimodal Reinforcement Learning
Experience: General
Pattern: full-time
Country:
apply Apply Now
Salary:
Status:

Frontier AI

Copy Link Report
degreeOND
loacation Zurich,, Switzerland
loacation Zurich,....Switzerland

Snapshot Are you a Research Engineer with a passion for Reinforcement Learning and Multimodality? Join Google DeepMind’s Frontier AI Unit! We are seeking a researcher to help us make learning efficient through conversational environments. While text-based reasoning has shown immense promise, we are moving the frontier toward image-grounded, multimodal, and retrieval-augmented conversational setups. You will bridge the gap between conversational learning and the visual domain, applying the latest RL methods to create scalable, semi-verifiable environments that power the next generation of our models (e.g., Gemini). About us Google DeepMind: Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, we’re 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. Frontier AI Unit: The Frontier AI Unit is responsible for building and scaling the next generation of our core models. Within this group, our team focuses on "conversationality" as a mechanism for efficient learning. We believe that learning conversationally transfers between environments. We are moving beyond Chain-of-Thought (CoT) and text-only setups to build multimodal, multi-turn reasoning capabilities, leveraging an ecosystem of autoraters and autousers to scale environment creation. The role We have strong evidence that conversational environments lead to better learning in a transferable way. However, we need to go beyond text. As a Research Engineer, you will play a pivotal role in expanding Meta Reinforcement Learning to multimodal setups. You will help us leapfrog current industry benchmarks by extending our focus from verifiable domains to semi-verifiable, multimodal domains (e.g., Lens, Image-grounded reasoning). This is an ecosystem play: you will leverage our advantages in autoraters and autousers to scale the creation of these conversational environments. You will be the bridge between the core conversational work and the specifics of grounding in the visual domain, moving our training infra from static data towards dynamic, multi-turn environments. Key responsibilities Multimodal RL Research: Design and implement novel RL algorithms that enable multi-turn reasoning and learning in multimodal (text + vision) environments. Environment Scaling: Contribute to the "ecosystem" of autoraters and autousers, building the infrastructure needed to generate high-quality, semi-verifiable training environments at scale. Strategic Application: Apply state-of-the-art methods to solve strategic problems, specifically closing the gap between single-turn and multi-turn embeddings (retrieval-augmented reasoning). Experimentation & Analysis: track, interpret, and analyze complex experiments, providing scientific rigor to our training pipelines. Collaboration: Act as a connector between teams (Google Research, Core, GDM GenAI), helping to build shared pipelines for conversational infrastructure that serve product needs in Search, Lens, and YouTube. What We Can Offer You Scientific Contribution: The opportunity to publish and contribute to the scientific community, specifically in the high-impact intersection of RL, Multimodality, and Reasoning. Scale & Resources: Access to world-class compute and the existing infrastructure of autoraters/autousers, allowing you to focus on innovation rather than building from scratch. Direct Impact: Your work will directly influence the reasoning capabilities of Google’s flagship models (Gemini), moving the needle on how models learn and interact with the world. Collaborative Culture: Work alongside world-leading experts in RL and Generative AI in a supportive, growth-oriented environment. About you We are looking for a Research Engineer who is not just technically proficient but deeply curious about the mechanics of learning. You should be up to date with the latest methods in RL and eager to apply them to messy, ambiguous, and high-impact strategic problems. You are comfortable bridging the gap between abstract research and concrete implementation. Essential Skills: PhD or Equivalent Experience: A PhD in Computer Science, AI, or related field, or equivalent practical experience, with a specific focus on Reinforcement Learning (RL). Proven Research Track Record: A history of scientific contributions (e.g., publications at NeurIPS, ICML, ICLR, CVPR) or significant contributions to state-of-the-art AI models. Multimodal Experience: Concrete experience working with multimodal models (vision + language) and understanding the specific challenges of grounding text in visual data. Engineering Excellence: Strong coding skills (Python, JAX/TensorFlow/PyTorch) and experience designing and executing complex experiments. Useful Skills: Retrieval & Embeddings: Experience with retrieval-augmented generation (RAG), embedding spaces, or search infrastructure. Multi-Agent Systems: Familiarity with self-verification, introspection, reflection, or multi-agent negotiation frameworks. Infrastructure: Experience building or scaling training environments, autoraters, or reward models. 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.

Other Ai Matches

Senior Technical Program Manager, Personal Intelligence Modeling Applicants are expected to have a solid experience in handling GenAI related tasks
Team Lead, Research Engineering, AI for Chip Design Applicants are expected to have a solid experience in handling GenAI related tasks
Technical Program Manager, Agentic Development Platform Applicants are expected to have a solid experience in handling GenAI related tasks
Technical Program Manager, Agentic Development Platform (Modeling & Evals) Applicants are expected to have a solid experience in handling GenAI related tasks
iOS/Swift Engineer, Project Janus Applicants are expected to have a solid experience in handling GeminiApp related tasks
Research Engineer - Multimodal Companion Agent Applicants are expected to have a solid experience in handling Frontier AI related tasks
Research Scientist/Engineer, Model Threat Defense Applicants are expected to have a solid experience in handling GenAI related tasks
Product Manager, Technical Intelligence, Google DeepMind Applicants are expected to have a solid experience in handling Office of the CEO related tasks
Product Manager, Growth & Discovery Platform, Gemini App Applicants are expected to have a solid experience in handling GeminiApp related tasks
Low power design engieer/micro-architect L5 Applicants are expected to have a solid experience in handling GenAI related tasks
Staff Mechanical Engineer, Gemini Robotics Applicants are expected to have a solid experience in handling Frontier AI related tasks
Staff Data Scientist, GeminiApp Applicants are expected to have a solid experience in handling GeminiApp related tasks
Staff Research Engineer, AI Products - Mountain View Applicants are expected to have a solid experience in handling GenAI related tasks
Research Engineer - GeminiApp Personalization Applicants are expected to have a solid experience in handling GeminiApp related tasks
Security Lead, Agentic Red Team Applicants are expected to have a solid experience in handling GenAI related tasks
Internal Communications, Unit Manager for Science and Frontier-AI Units Applicants are expected to have a solid experience in handling Central Operations, Responsibility, and Engagement related tasks
Machine Learning Software Engineer, GeminiApp Agents and Tool Use Applicants are expected to have a solid experience in handling GeminiApp related tasks
Senior Staff Data Scientist, GeminiApp x-Product Applicants are expected to have a solid experience in handling GeminiApp related tasks
Technical Program Manager: GeminiApp Automation Applicants are expected to have a solid experience in handling GeminiApp related tasks
Product Manager, Gemini in Chrome, Gemini App Applicants are expected to have a solid experience in handling GeminiApp related tasks
US Frontier Policy Lead Applicants are expected to have a solid experience in handling Central Operations, Responsibility, and Engagement related tasks
Product Manager, Personalization, Gemini App Applicants are expected to have a solid experience in handling GeminiApp related tasks
AI Product Designer, GeminiApp iOS Core Experience Applicants are expected to have a solid experience in handling GeminiApp related tasks