Mangesh Bide

Mangesh Bide

Software Engineer — Backend & Applied AI

House Works Technology · Remote (India)

I ship backend and AI systems end to end — from the data model to the infra they run on. By day that's Django, PostgreSQL, and AWS on a production healthcare product; on my own time I take FastAPI services, RAG pipelines, and tool-calling agents from idea to a live URL.

GitHub Activity

Mangesh's GitHub Contributions

Latest Writing

Selected Work

Mira

Mira

Browser-based voice agent (Tavus CVI) backed by a FastAPI service that runs seven tool-calling booking functions, persists transcripts, and writes an LLM call summary.

FastAPI Python Tavus CVI +4
View Details

Fieldnotes

Fieldnotes

LLM pipeline that scores a job posting against your resume and returns an APPLY / CONSIDER / SKIP verdict with evidence — shipping both a deterministic DAG and an agentic planner→executor→synthesizer flow over the same steps.

FastAPI Python Gemini +3
View Details

HIPAA Guardian

HIPAA Guardian

PHI/PII detection engine that scans code, logs, and API responses for the 18 HIPAA Safe Harbor identifiers — built to catch leaks in developer artifacts before they ship.

Python HIPAA / PHI Static Analysis +2
View Details

What I work with

Backend & APIs

Python, Django, FastAPI, and PostgreSQL — auth, data modeling, and APIs built to hold up in production.

Applied AI & Agents

LLM applications, RAG pipelines, and tool-calling agents — wiring models into products that do real work.

Infrastructure & Cloud

Terraform and Docker on AWS, plus a k3s homelab on OCI — reproducible infra and CI/CD from zero.

Why this site exists

I learn things by building the smallest version that actually runs, then writing down what broke. This site is where both halves end up — the projects and the post-mortems. If it saves you an afternoon, even better.