Introduction
ActiveViam has shown that its proprietary software Atoti is the leading technology to interactively analyse datasets from Gigabytes to Terabytes. Atoti can harness the largest machines of Cloud platforms and on-premise DataCenters to make all the CPUs work at a blazing speed on their Terabyte RAMs filled with client data.
As Atoti UI continues to evolve, monitoring the size and structure of our JavaScript bundles is critical to ensuring a fast and responsive user experience. Manual checks are error-prone and unsustainable at scale. Automating this process will help enforce performance standards across teams, prevent unintentional bloat, and increase transparency in the development workflow. Your work will directly contribute to improving product quality and developer efficiency.
Expected Work
We are offering an internship focused on bridging user input and UI logic through LLM-driven interactions. The goal is to define a structured, extensible interface for frontend user actions that can be serialized and triggered based on LLM responses. Rather than relying on custom server-side endpoints to support new features, this architecture enables the LLM to directly produce frontend instructions, simplifying development and enabling faster UI iteration.
Responsibilities
- Design a type-safe interface to represent high-level UI actions (e.g., selecting filters, navigating tabs, configuring widgets)
- Define serialization formats for these actions and ensure compatibility with our existing frontend architecture
- Collaborate with the team building the LLM server to consume user input and return valid, typed action objects
- Integrate the interface with the Atoti UI to interpret and execute serialized actions
- Build example prompts, test cases, and tooling to validate action round-trips from LLM to UI
What You’ll Learn
- Hands-on experience designing interfaces between frontend applications and LLMs
- Knowledge of command pattern architecture and JSON-based protocols
- How to bridge structured data and natural language input in real-world applications
- Exposure to cutting-edge AI/UX integrations in a production-quality web application
Qualifications
- Proficiency in TypeScript and modern React
- Interest in LLMs, natural language interfaces, or declarative UI architectures
- Strong design and communication skills to work on APIs and cross-functional interfaces
- Bonus: Experience with prompt engineering, JSON schema design, or OpenAI tools
About ActiveViam
ActiveViam provides business users with instant insight into large volumes of fast-moving data for timely and context-aware decision-making.
Founded in 2005, ActiveViam employs over 150 people in its five offices of New-York, London, Paris and Singapore. We expect sustained growth in 2025 and will continue hiring the best talents from the top schools.
