Platform Engineer

Platform Engineer

San Francisco, CA, USA • Full-time

ThirdLayer is solving one of the hardest problems in deploying agents: AI models are generic, but people's work and processes are specific. Our product, Dex, embeds within your computer and team, ingesting a continuous stream of data across your browser and work apps to understand how you actually operate. So when you delegate tasks, agents know exactly the context of where information lives and how decisions get made. We're a deeply technical team with a high bar for talent and a shared belief that exceptional people are the foundation of everything we build.

The Role

Our platform turns raw user activity into structured process knowledge that agents can act on. We're looking for engineers who have gone deep on production AI systems. Maybe you've built context pipelines that handle messy real-world data, shipped agent systems that users actually rely on, or designed the evaluation infrastructure to know whether any of it is working. You'll own core parts of the platform, work closely with customers to pressure-test what we're building, and fold learnings back into the product. The work spans continuous context capture, agent orchestration, feedback loops, and the systems that tie them together.

What You'll Do

• Own and evolve our context capture and learning pipeline, building new capabilities with customers and pulling patterns back into the platform.
• Ship agent systems and AI-powered workflows from early prototype through production.
• Partner with customers to find the highest-leverage problems and build solutions that stick.
• Build agentic features that let agents learn from user behavior, adapt to new workflows, and take action on behalf of users.
• Build evaluation and reliability infrastructure so we know when agents are ready to act autonomously vs. when they should ask.
• Design systems that handle real-time ingestion and orchestration at scale.
• Shape the technical direction of the product.

What We're Looking For

• You've built production AI or LLM-based systems and can walk through the engineering tradeoffs in detail.
• You've taken something from idea to production and can talk about how it changed along the way.
• You're drawn to open-ended problems where the solution isn't handed to you.
• Interest in how systems get smarter over time: feedback loops, prompt engineering, context design.
• Experience building agents or autonomous systems.
• As comfortable reading a paper as writing production code.
• Strong communicator who can talk through technical decisions with both teammates and customers.