Nirvahn ThakurMHSA

I help organizations implement AI properly, and I'm also the engineer who builds it.

Enterprise Architect @ Workday · Charlotte, NC

Identification
Portrait of Nirvahn Thakur

Nirvahn Thakur

Enterprise Architect · AI Engineer

ID no.
NT-2026
Clearance
AI · Data · Healthcare

Systems I've built and run

Press and hold. Every slip opens a case study.

Sprayed 00

  • NTHNPythonFastAPI

    7production modules shipped

    Enterprise healthcare analytics platform

    Lead developer on a production analytics platform, from live data to AI agents.

  • MIGRPythonFastMCP

    2–3 daysof manual scripting replaced per migration

    Warehouse migration MCP tool

    An MCP server that automates moving a data warehouse, starting with Snowflake to Databricks.

  • CHRTSwiftUISwiftData

    0patient records stored on the server

    ChartHaven

    A patient-owned medical records app whose AI answers only from your own records.

  • ROUTPythonR

    d = 0.64effect size vs closest-hospital routing

    AI hospital routing

    Patient routing that weighs specialty fit and ED crowding, not just distance.

  • HRMSHermes AgentClaude

    8 minfrom a red build to a green fix, untouched

    Hermes Agent

    A personal AI assistant I text or talk to. It plans my to-do list, waits for my yes, and hands coding to Claude Code.

  • HMLBDockerPrometheus

    5machines watched on a private mesh VPN

    Self-hosted homelab

    A private, fully monitored homelab of five machines, running the services I depend on.

01 — ABOUT

About me

I'm an Enterprise Architect at Workday, where I help organizations turn AI into working systems across HR, finance and operations.

Before that I was lead developer on a production healthcare analytics platform, shipping agents, MCP tooling and the data pipelines behind them.

I came to this through healthcare: EMT, then pre-med psychology, then a Georgetown MHSA, so I know the care pathways these systems have to fit.

  1. EMT
  2. Psychology
  3. MHSA
  4. AI engineering
  5. Enterprise architecture

Mentor with Big Brothers Big Sisters, 2016–2020. Languages: English, Spanish, Hindi.

Education

Georgetown University

MS, Health Systems Administration (MHSA)

2024 – 2026

Clemson University

BS, Psychology (pre-med track), minor in Business Administration

2020 – 2024

NCOAE

EMT (BLS) certification

2022

02 — SKILLS

The stack

AI / LLM13
  • Claude Code · 1

    Daily driver

    Primary development workflow, with 15 custom slash commands, hooks and multi-agent orchestration.

    See it in use →
  • Claude API · 2

    Production

    Agents and apps built on the Anthropic API.

  • LangChain · 3

    Production

    Agentic ETL at Nuthan; certified.

    See it in use →
  • Azure OpenAI · 4

    Production

    Chat and extraction on GPT-4-class models behind production agent backends.

    See it in use →
  • RAG · 5

    Production

    Record-grounded chat that never truncates retrieved context.

    See it in use →
  • Embeddings · 6

    Production

    bge-large retrieval that lifted recall@5 from 0.929 to 1.000.

    See it in use →
  • Model evaluation · 7

    Production

    Gold sets, F1 and decline-rate evals, and A/B comparisons that pick the model.

    See it in use →
  • Local models · 8

    Working

    Benchmarked Llama, Mistral and Phi; fine-tuned and A/B-tested models on Apple silicon; Ollama at home.

    See it in use →
  • LoRA fine-tuning · 9

    Working

    Fine-tuned 7B/8B adapters locally, then retired them when a 14B base won the A/B.

    See it in use →
  • MLX serving · 10

    Working

    Self-hosted 14B model on Apple silicon with speculative decoding (about 1.8x faster).

    See it in use →
  • Code knowledge graphs · 11

    Production

    Codebases as queryable graphs; agents read the graph report instead of raw files.

    See it in use →
  • Token cost engineering · 12

    Production

    Output compression, usage profiling and MCP schema pruning after a 97-session audit.

    See it in use →
  • Voice pipelines · 13

    Working

    Offline Whisper speech-to-text and Piper text-to-speech over the Wyoming protocol.

    See it in use →
Agents & MCP10
  • MCP · 14

    Production

    A 10-tool migration server over Streamable HTTP, with the UI as an MCP client.

    See it in use →
  • CrewAI · 15

    Production

    Multi-agent ETL automation; certified.

    See it in use →
  • LangGraph · 16

    Working

    Multi-stage agent graphs with a deterministic verifier against hallucination.

  • Agent observability · 17

    Production

    Execution tracing, failure monitoring and token-level cost tracking.

    See it in use →
  • Langfuse · 18

    Production

    Traced every stage of agent pipelines in self-hosted deployments.

  • Multi-agent orchestration · 19

    Production

    Agent teams and git-worktree-isolated workers with a completion relay.

    See it in use →
  • Claude Code hooks · 20

    Daily driver

    Hooks on 14 event types, including a per-turn canary against context rot.

    See it in use →
  • Pydantic · 21

    Working

    Structured LLM outputs; certified.

  • AutoGen · 22

    Working

    Multi-agent design patterns.

  • OpenRouter · 23

    Working

    Model routing and fallback in Hermes Agent's first model chain.

    See it in use →
Data12
  • Python · 24

    Daily driver

    Data pipelines, agents and backends.

  • SQL · 25

    Daily driver

    Pipelines and analytics queries.

  • Snowflake · 26

    Production

    Migration source; SnowPro Core certified.

    See it in use →
  • Databricks · 27

    Production

    Migration target with COPY INTO.

    See it in use →
  • Cortex Search · 28

    Production

    Managed vector search on Snowflake for document RAG.

  • PostgreSQL · 29

    Production

    Backends for analytics and ChartHaven accounts.

    See it in use →
  • Supabase + RLS · 30

    Production

    Row-level security on every table and an idempotent provisioning script.

    See it in use →
  • SQLite · 31

    Production

    Local-first stores: job queues in WAL mode, agent memory and trade logs.

    See it in use →
  • ETL · 32

    Production

    Three manual processes automated with agents.

    See it in use →
  • CouchDB sync · 33

    Production

    Self-hosted end-to-end encrypted notes sync across four devices.

    See it in use →
  • Knowledge pipelines · 34

    Production

    Dedupe-on-ingest, document-to-Markdown conversion and nightly health checks.

    See it in use →
  • Market data systems · 35

    Working

    Kalshi and Polymarket clients, macro feeds, half-Kelly sizing and a risk module.

    See it in use →
Full-stack11
  • FastAPI · 36

    Production

    Backends for analytics and the migration tool.

    See it in use →
  • Node / Express · 37

    Production

    ChartHaven backend.

    See it in use →
  • React · 38

    Production

    Front ends for analytics and tooling.

  • TypeScript · 39

    Production

    Front ends and this site.

  • Next.js · 40

    Production

    FastAPI-backed web apps, and this site.

  • Tailwind · 41

    Production

    Design systems on Tailwind v4.

  • SwiftUI · 42

    Working

    ChartHaven iOS app with SwiftData, PDFKit and Vision OCR.

    See it in use →
  • Server-sent events · 43

    Production

    Live job logs and streamed chat tokens.

    See it in use →
  • asyncio · 44

    Production

    Background jobs with bounded-queue backpressure.

    See it in use →
  • Auth & MFA · 45

    Production

    bcrypt, TOTP MFA, refresh tokens and least-privilege database roles.

    See it in use →
  • API integration · 46

    Production

    Todoist, Gmail OAuth and the Obsidian REST API, with idempotent two-way sync.

    See it in use →
Infra / DevOps13
  • Docker · 47

    Production

    Self-hosted services and analytics backends.

    See it in use →
  • n8n · 48

    Production

    A 26-node two-way task sync, email triage and note-sync workflows.

    See it in use →
  • Mesh VPN · 49

    Production

    Private network across every node.

    See it in use →
  • Prometheus + Grafana · 50

    Production

    15-second scrapes and generated, query-validated dashboards.

    See it in use →
  • Alerting & watchdogs · 51

    Production

    Two-strike alerts, a dead-man heartbeat and a stale-workflow detector.

    See it in use →
  • Linux networking · 52

    Production

    Root-caused a gateway fault with tcpdump and iptables tracing.

    See it in use →
  • Root-cause analysis · 53

    Production

    Eight documented incidents with named root causes.

    See it in use →
  • CI/CD · 54

    Production

    GitHub Actions, Dependabot, pre-commit with gitleaks, and an iOS build check.

    See it in use →
  • Testing · 55

    Production

    jest and supertest with a coverage gate; pytest regression suites.

    See it in use →
  • AppSec · 56

    Production

    Semgrep SAST plus weekly ZAP, Nuclei and authorization-probe DAST.

    See it in use →
  • Home Assistant · 57

    Production

    Smart-home hub on a Pi 5 with Matter devices and an MQTT bridge.

    See it in use →
  • Render / Vercel · 58

    Production

    Hosting for backends and this site.

  • Linux / Pi · 59

    Production

    Raspberry Pi 5 and Pi 4 nodes.

    See it in use →
Healthcare7
  • HIPAA-oriented design · 60

    Production

    Encryption, audit logging and least-privilege access in ChartHaven.

    See it in use →
  • Applied cryptography · 61

    Production

    Secure Enclave P-256, ECDH/HKDF and AES-256-GCM sealing.

    See it in use →
  • EMT (BLS) · 62

    Production

    Frontline care at Vital Care EMS.

  • Interoperability · 63

    Working

    FHIR R4 bundles with LOINC and ICD-10 coding; C-CDA record import.

    See it in use →
  • Health systems · 64

    Production

    Georgetown MHSA: care pathways and payer operations.

  • Statistics · 65

    Working

    t-tests and effect sizes across 500 simulated cases.

    See it in use →
  • Decision modeling · 66

    Working

    A utility function weighing severity, specialty fit, transport and ED delay.

    See it in use →

04 — EXPERIENCE

Where I've worked

The path

  1. EMT
  2. Psychology
  3. MHSA
  4. AI engineering
  5. Enterprise architecture
  • Technology
  • Clinical
  • Academic
  1. Jul 2026 — Present

    Enterprise Architect

    Workday · Charlotte, NC (Technology)

    • Help customer organizations design and deploy AI-driven solutions across HR, finance and operations.
    • Translate platform and AI capabilities into clear strategy for business and technical stakeholders.
  2. Jun 2024 — Jul 2026

    AI Engineer

    Nuthan Technologies · Charlotte, NC (Technology)

    • Lead developer of an enterprise healthcare analytics platform: 7 production modules, including an AI Insights Agent and an agent-observability layer.
    • Automated 3 manual ETL processes with LangChain and CrewAI agents, cutting analyst prep from about 4 hours to under 20 minutes per cycle.
    • Shipped an MCP tool for cross-warehouse migration (Snowflake → Databricks), replacing 2–3 days of manual scripting per migration.
  3. Feb 2023 — May 2024

    Emergency Medical Technician

    Vital Care EMS · Upstate, SC (Clinical)

    • Analyzed 6 months of dispatch data to rebalance crew shift coverage, cutting average response time about 12% across 3 stations.
    • Provided basic life support under time-critical conditions, with patient care records kept to state and federal standards.
  4. Aug 2022 — Aug 2023

    Academic Tutor, Organic Chemistry

    Clemson University (Academic)

    • CRLA Level 2 certified tutor.
  5. Dec 2021 — Jan 2022

    Student Intern

    Atrium Health (Clinical)

    • Clinical rounds in pediatric congenital heart disease.
  6. Jun 2019 — Aug 2020

    Intern

    The Neurological Institute (Clinical)

    • Supported clinical trials.
    • Researched and presented on Myasthenia Gravis to the board of physicians.

Education

  • Georgetown University

    MS, Health Systems Administration (MHSA)

    2024 – 2026

  • Clemson University

    BS, Psychology (pre-med track), minor in Business Administration

    2020 – 2024

  • NCOAE

    EMT (BLS) certification

    2022

Certifications

  • SnowPro Core (Snowflake)
  • GitHub Foundations
  • Claude Code in Action
  • Developing Applications with LangChain
  • Pydantic for LLM Workflows
  • Multi AI Agent Systems with CrewAI

Also completed

  • Building with the Claude API (Anthropic)
  • Claude Code 101 (Anthropic)
  • AI Fluency: Framework & Foundations (Anthropic)
  • Introduction to Agent Skills (Anthropic)
  • Introduction to Claude Cowork (Anthropic)
  • AI Agentic Design Patterns with AutoGen (DeepLearning.AI)

05 — ACHIEVEMENTS

Proud moments

  • 01

    7

    Production modules shipped on an enterprise healthcare analytics platform

    2024 – 2026

  • 02

    28

    Medical specialties of live HCP data behind one real-time backend

    2024 – 2026

  • 03

    4h → 20m

    Analyst prep per cycle, after agents automated three ETL processes

    2024 – 2026

  • 04

    2–3 days

    Of manual scripting replaced per warehouse migration by an MCP tool

    2024 – 2026

  • 05

    8 min

    From a red CI build to a green fix PR with nobody touching it: my agent planned, fixed and texted "Ready"

  • 06

    9 s → 0.28 s

    Memory recall per new chat for that agent, after moving memory to an always-on server

  • 07

    2,710

    Container restarts a ping-only monitor never saw in my homelab; health checks now catch it

  • 08

    0% → ~98%

    Task-sync success after I found a silent outage and added a relauncher that self-heals

  • 09

    ~12%

    Faster average EMS response across 3 stations after shift rebalancing

    2023 – 2024

  • 10

    d = 0.64

    Effect size for AI hospital routing vs closest-hospital, across 500 simulated cases

    2026

  • 11

    6

    Certifications: SnowPro, GitHub, LangChain, CrewAI, Pydantic, Claude Code

    2024 – 2026

  • 12

    MHSA

    Master of Health Systems Administration, Georgetown University

    May 2026

06 — CONTACT

Let's build something.

Open to a conversation about enterprise AI, agents and healthcare systems. The fastest way to reach me is email.

Press ⌘K anywhere to jump around.