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 systems. * Evaluation frameworks for agent performance. * Memory and personalization layer for workflows ## Requirements * Research/work experience with LLMs, modern AI frameworks, and/or ML. * Experience with prompt engineering strategies. * Strong foundation in Python and TypeScript. ## Sample Projects * Agentic systems that predict and execute users’ next steps in complex workflows. * A searchable, self-updating memory store for personalized browser agent behaviour. * Designing intuitive interfaces for how users should delegate and override AI actions. * 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.
Job details are sourced from the employer's original posting.
Open job postingAbout the company
Dex is a company focused on transforming requirements into concrete shipped work, emphasizing data integrity, error paths, API evolution, and operational concerns. They look for engineers who can independently own and ship end-to-end product slices with minimal supervision.