to
Senior Software Engineer Zenlytic
- Built Zenlytic's LLM-powered chat feature end-to-end (Python/Flask, React/TypeScript) — query generation, prompt/context assembly, a streaming response pipeline, and tool-call visualization in the chat UI — as part of a 7-person team.
- Owned the semantic data model editor that keeps the chat agent on verified metric definitions instead of ad-hoc SQL, evolving it from a raw YAML editor to validated forms with readable errors, then to an AI flow where users approve the agent's proposed changes as pull requests.
- Interviewed internal and external users to scope and design the editor, and reworked its backend to validate and save per-file changes; more clients began editing their own data model, with far fewer “is the app broken?” reports.
- Built the explore (ad hoc query) and dashboard UIs over the semantic layer, offering only the fields and dashboard filters that can be joined, so no question a user builds compiles to invalid SQL.
- Served as on-call responder for production incidents, using session-replay tooling (LogRocket) to diagnose real user failures and shape observability priorities through direct customer conversations.
- Partnered directly with customers on adoption issues and helped define company-wide coding standards for testing, accessibility, and static analysis.
- React.js
- TypeScript
- Python
- Flask
- Design Systems
- Data Visualization
- Chakra UI
- Vite