Research Scientist, Agentic AI & LLM Systems

Google; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Job summary

Google’s Stitch team in Mountain View is seeking a Research Scientist to shape a long-term research agenda around agentic AI, planning, and advanced ML methods. You will set up large-scale experiments and architect novel systems as you push the boundaries of AGI-relevant capabilities within Gemini and related projects.

You will also publish findings, collaborate with internal programs and external researchers, and contribute to tool-building and evaluation benchmarks that drive real-world

Qualifications

• PhD in Computer Science or related field, or equivalent practical experience.
• 2 years of experience leading a research agenda.
• Experience with modern ML frameworks such as JAX or PyTorch.
• Experience in agentic AI (planning, tool use, memory) and RL areas.
• One or more scientific publication submissions for conferences, journals, or public repositories (CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).

Responsibilities

• Define and pursue a long-term applied research agenda to overcome fundamental limitations of LLMs in long-horizon reasoning, planning, and tool use for complex software engineering tasks.
• Design and implement novel agentic architectures, exploring automated workflow optimization, multi-agent decomposition, and self-improvement.
• Explore memory and context management techniques for reasoning over large codebases.
• Lead research into synthetic data generation, verification methods/environments and rewards for Gemini improvement.
• Develop high-fidelity evaluation frameworks measuring agent impact on software quality and developer productivity.

Skills

PhD or equivalent

Lead research agenda

JAX or PyTorch

Agentic AI / RL

Publications

Education

PhD in Computer Science

Job description

Google’s Stitch team in Mountain View is seeking a Research Scientist to shape a long-term research agenda around agentic AI, planning, and advanced ML methods. You will set up large-scale experiments and architect novel systems as you push the boundaries of AGI-relevant capabilities within Gemini and related projects.

You will also publish findings, collaborate with internal programs and external researchers, and contribute to tool-building and evaluation benchmarks that drive real-world