2026 Summer AI/ML Engineer Intern
San Francisco, CA at a glance
- Rent
- #2 of 51$2,680/mo+46% vs US avg
- Weather
- #17 of 51295 mild days0 hot · 0 cold
- Income tax
- #1 of 5113.3% top rateCalifornia
What you need
- RL environments, LLMs, modern AI frameworks, or ML experience
- Experience with prompt engineering strategies
- Strong foundation in Python and TypeScript
What you'll do
- Build browser agent and tool-calling multi-agent systems
- Build evaluation frameworks for memory, efficiency, and accuracy
- Build memory and personalization layer for workflows
2026 Summer Research Engineer Intern
Join us in pushing the boundaries of what's possible with LLMs and browser-native AI. You'll work on cutting-edge problems in agent systems, context handling, and tool use, while collaborating directly with our research team to bring novel approaches to production.
What You'll Build
- Browser agent and tool-calling multi-agent systems.
- Evaluation frameworks for memory, efficiency, and accuracy.
- Memory and personalization layer for workflows
Requirements
- Research or work experience with RL environments, LLMs, modern AI frameworks, and/or ML.
- Experience with prompt engineering strategies.
- Strong foundation in Python and TypeScript.
Sample Projects
- Designing and creating tool-calling environments to evaluate and benchmark agent systems
- Agentic systems that predict and execute users’ next steps in complex workflows.
- Mapping user paths on real world software to API functionality and action trajectories.
- A searchable, self-updating memory store for continuously learning agents.
- A system to interpret DOM snapshots, mouse click events, and keyboard inputs to select browser actions.
- A context composer that feeds relevant info into LLM prompts based on user interactions, page content, and memory.
Optimize your resume for this job
Get a match score and the keywords you're missing
About Thirdlayer
ThirdLayer is the learning and alignment layer for enterprise AI. We continuously ingest and structure messy organizational context, complex operational processes, and siloed, permission-sensitive data, then grade agents against the outcomes each company cares about. Every interaction becomes feedback that helps agents improve over time. Companies use ThirdLayer to power their internal agents or embed it into the AI products they’re building. We give agents the context, evaluations, and learning loops they need to stay aligned with each organization and deliver better outcomes with every run.
Similar roles
