# Nayab Rehmat

Nayab Rehmat is a software engineer who has built agentic AI systems in production healthcare. Work includes Ambora, Backlog, and CRTX, plus downloadable Claude Code skills.

Location: Austin, TX. Open to SF or NYC.
Email: nayabrehmat28@gmail.com
GitHub: https://github.com/mnr282001
LinkedIn: https://www.linkedin.com/in/nayab-rehmat/
X: https://x.com/m_nayabrehmat

## About

Software engineer at Inception, where I ship agentic AI and the backend a national clinic network runs on every day.

I like the part of the job where a vague problem turns into something people actually use, so I design and build the whole thing, from the data model to the last piece of copy. Nights and weekends I build products of my own.

## Products

### Ambora

Code with your hands in your pockets. Describe a change by voice or text from your phone; Ambora plans the work, explains its approach, then writes and tests it on a branch so it's waiting when you sit back down. Auth, payments, and config changes sit behind explicit approval gates, and nothing reaches GitHub without you saying so.

Stack: Next.js, Claude, GitHub API, Supabase
URL: https://ambora.io

### Backlog

Your reading, back as a morning letter. Share an article from any app and it disappears into a queue; at 6am you get one edited five-minute email covering everything you saved, with editorial notes on what's worth your time and links straight to the originals. No feed, no recommendations, the only thing in it is what you chose.

Stack: Next.js, TypeScript, Supabase, Claude, Resend
URL: https://backlog-hazel-beta.vercel.app

### VCDB

A venture-firm directory built for job hunting, sitting on top of the pipeline that fills it in. I imported 1,350 firms as names alone and let a worker do the rest: it resolves each firm's domain from Brave search results, scores the match on name-token overlap and venture context, then probes the site for portfolio, careers, and jobs-board URLs and tags the platform behind them, Getro, Ashby, Greenhouse, or Lever. Anything under a 0.7 confidence gate goes to a review queue instead of the directory. The worker claims batches of 100 from a retrying job queue in Postgres on a ten-minute GitHub Actions cron, so the whole backfill ran unattended and new firms enrich themselves. The Next.js front end reads the table with the anon key only, filtered, sorted, and paginated straight from the URL.

Stack: Next.js, Python, Supabase/Postgres, Brave Search API, GitHub Actions
URL: https://vcdb-nine.vercel.app

### GridScope

A grid-intelligence platform that fuses three government data sources, the ERCOT interconnection queue, TCEQ air permits, and PUCT dockets, into one de-duplicated, geolocated view of 1,100+ Texas projects across ~12.7k historical snapshots. I led the backend. None of the three sources share an ID or a coordinate, so I built coordinate-free entity resolution using token-set Jaccard matching on name and county, tiered into resolved, review, and unresolved, plus two-tier geolocation from Census county centroids to exact EPA FRS coordinates so every project still got a map pin. I owned ingestion end to end: multi-sheet ERCOT .xlsx reports, the TCEQ Socrata API, and PUCT docket filings, normalized into snapshotted Postgres tables.

Stack: FastAPI, Supabase/Postgres, MapLibre

### CRTX

A full-stack RAG platform for semantic search over your own documents. Upload PDFs and URLs; CRTX chunks, deduplicates, and embeds them for question-answering over a private corpus. Supabase Auth, JWT-gated routes, and share links that keep ingest and query permissions separate. I piloted it with a client, mapped their document-review workflow, and shipped features straight from their feedback.

Stack: FastAPI, Next.js, LangChain, Pinecone, Redis, Supabase
URL: https://crtx.chat
Source: https://github.com/mnr282001/crtx

## Claude Code skills

### visual-design-loop

A build-and-refine process for web UI that keeps it from looking AI-generated. It closes the three gaps that usually cause it: pin down a real brief before writing code, lock a token system before writing CSS, then iterate against actual screenshots instead of trusting the markup. Ships with a seven-pass critique rubric, a guide to turning inspiration images into a transferable brief, and a Playwright capture script that audits every pass for overflow, contrast failures, small tap targets, token sprawl, and console errors.

Command: /visual-design-loop
Download: https://nayabdev.com/skills/visual-design-loop.zip
Page: https://nayabdev.com/skills/visual-design-loop/

### plain-outbound-writing

A final pass for anything a person will read as a message from you: email, Slack, DMs, cover letters, outreach. Most AI-sounding writing isn't wrong, it's performed. It keeps signaling that a point was made instead of just making it. This names each move that produces the effect, from the "that's not X, that's Y" reveal to stacked sentence fragments to image pairs that stand in for the actual instruction, and gives the plain replacement for each.

Command: /plain-outbound-writing
Download: https://nayabdev.com/skills/plain-outbound-writing.zip
Page: https://nayabdev.com/skills/plain-outbound-writing/

## Experience

### Software Engineer, Inception Fertility

2023 — 2026 · Austin, TX

- Built an autonomous error-remediation agent (TypeScript) for the production mobile app: nightly Sentry API queries filtered by error volume, an LLM extraction pass with retry-on-validation-failure producing structured context, handed to a coding agent that opened one scoped PR per fix. 5 fixes merged; every PR gated on human review.
- Led migration of the legacy patient-facing app to React Native (TypeScript) across a 110+ clinic network with zero downtime; ran the feature-parity assessment mapping 8 major feature categories and their underlying actions into the migration roadmap, and drove sequencing decisions on what shipped when. End-user satisfaction rose 2.7 → 4.1.
- Directed a three-engineer build and owned delivery infrastructure end to end (CI/CD, EAS build and release pipeline, App Store submission, observability via Datadog and PostHog) on a backing architecture I designed around Supabase-backed services and Node.js API gateways into AWS ECS.
- Owned backend services and REST APIs (Python, AWS Lambda, DynamoDB, Cognito) serving 50,000+ monthly active patients across a 110+ clinic network.
- Carried production on-call in a live medical environment where downtime halted clinic operations; diagnosed and resolved multiple production incidents under time pressure while maintaining uptime targets.
- Built the integration and reliability layer between patient-facing services and eIVF, a decades-old EHR with undocumented behavior and no ability to change the upstream system; reverse-engineered its semantics and designed around its failure modes.

### Software Engineering Intern, ChampionX

2022 · Houston, TX

- Built a full-stack asset-provisioning tool for oilfield operations (React, TypeScript, Node.js), working directly with field-operations stakeholders to translate on-site workflows into a production system.
- Implemented real-time data streaming and REST APIs to surface live equipment status and asset allocation across distributed oilfield sites.

### Teaching Assistant, Texas A&M College of Engineering

2020 — 2022 · College Station, TX

- Supported instruction of Python fundamentals (ENGR 102) for 96 engineering students, translating programming concepts for non-CS audiences across lectures and written feedback.
- Led two weekly debugging sessions, diagnosing and resolving students' code issues in real time.

## Education

B.S. in Computer Science and Engineering, Texas A&M University, College Station, TX

## Toolkit

- AI / ML: LLM APIs (Claude, OpenAI, Gemini), RAG pipelines, LangChain, LlamaIndex, agentic frameworks, multi-agent orchestration, MCP, evals
- Frontend: React, React Native, Next.js, TypeScript, Tailwind CSS
- Backend: Node.js, FastAPI, REST, GraphQL, AWS Lambda, Python microservices
- Data: PostgreSQL (Supabase), DynamoDB, Pinecone, Redis, schema design
- Platform: AWS, Docker, GitHub Actions, CI/CD, OAuth / JWT / SSO, HIPAA-compliant systems
- Observability: Datadog, PostHog, Sentry, logging pipelines
