Danish Siddique
Senior Full-Stack Engineer · Agentic AI
I'm a full-stack engineer with 5+ years building products end to end. React and TypeScript on the frontend, Node and Django on the backend, and the database design underneath. For the last few years I've been at (formerly Mynd), a mental-health platform used by 200+ therapists and their clients. I owned a lot of the core product there: live video sessions, scheduling, billing, and the AI features that run on top of them.
Lately most of my work has been agentic. I built a RAG system grounded in real clinical context, an in-app assistant that can take actions on the user's behalf, and a pipeline that turns a Sentry alert into a reviewed PR. I also built and launched (joinroundzero.com), a job-prep platform with honest resume tailoring, cited company research, and live AI voice interviews that score and coach candidates before the real thing. I use Claude Code and Cursor every day to move faster, but not to do the thinking. I still read every line before it ships.
Experience
- Built and scaled Kindred Practice (formerly Mynd), an AI-driven practice-management platform, to 200+ therapists and the thousands of clients they serve; owned scheduling, billing, clinical documentation, and AI features end-to-end.
- Own full-stack delivery of Kindred Workplace, an emotional-intelligence platform for teams, across React, Node.js (TypeScript), and Django, shipping features from architecture through production.
- Architected an event-driven backend on Node.js (TypeScript), Django, and AWS Lambda, integrating real-time video, transcription, and chat via LiveKit, AWS Chime, and Deepgram to power live therapy sessions.
- Deployed multiple production RAG pipelines (pgvector, custom chunking, eval-driven iteration) across clinical, support, and internal-knowledge surfaces, cutting p95 response latency ~40% and LLM/API spend ~30% via prompt caching and model routing.
- Built an in-app AI assistant that takes real actions inside the product through tool calls, with structured outputs, scoped permissions, and per-call guardrails to keep it production-safe.
- Shipped org-wide developer-loop automations: Sentry incidents and Gleap tickets route through Goose agents that reproduce, implement, and open ready-to-review pull requests, auto-handling 30+ incidents and tickets a month and cutting incident-to-fix time significantly.
- Authored the team's shared Cursor rules and Claude Code skills that encode Kindred's conventions, keeping feature velocity around 2-3x and cutting new-hire ramp from weeks to days.
- Built a RAG-powered customer support chatbot on OpenAI, FastAPI, and PostgreSQL. Improved response accuracy and significantly reduced manual support load.
- Designed and shipped cross-platform React interfaces for the SaaS product.
- Integrated third-party APIs into SaaS workflows on AWS Lambda using a serverless architecture, enabling automation and data sync across platforms.
- Built an ML-based trademark infringement detection system on logos. Reached 85%+ accuracy. Reduced manual review effort by ~70%.
- Delivered multiple applications across Node.js, React, Flask, and PostgreSQL for legal and marketing automation.
- Refactored PostgreSQL and MongoDB databases. Improved query performance and scalability under growing data loads.