How this works

AI assistant for Dhavan’s published portfolio material. Answers can be incomplete or wrong, so do not submit confidential code or data.

Your questions go through Hugging Face, and a model run by DeepInfra writes the answers. Chats may be retained for about 30 days to operate, debug and improve the assistant; DynamoDB TTL deletion is approximate. Formspree processes contact and hire-form submissions. Details are in the privacy policy.

Use the suggested questions or ask about published projects, credentials, and engagements.

About

You work with the person who built it.

I’m Dhavan Shah, an independent AI systems engineer. I take LLM features and agents from demo to dependable production: measured reliability, a spending limit per customer, and a record of every decision.

Tell me what’s blocking you

Dhavan Shah The first 30 minute call is free, and if I can’t help, I say so before you pay anything.

Dhavan Shah

Track record.

20+
customer workflows where I architected production LLM features at DevRev
Top 0.5%
Kaggle Competitions Expert: 701 of 203,686, with 3 bronze medals
~2,500
automated tests across the KazenAI product
MSc
Data Science, University of Zurich

  • Dec 2025 to now

    Founder and AI systems engineer

    KazenAI, remote from Mumbai

    Built Agent FinOps, a hard spending limit for every customer’s AI, with run receipts for every allow and deny. About 2,500 automated tests across the product, and open source Python SDKs on PyPI. kazenai.com

  • Jan to Nov 2025

    Applied AI Engineer

    DevRev, Chennai

    Architected production LLM features across 20+ customer workflows. Delivered monitoring, feedback loops and structured failure recovery for production LLM modules.

  • Jul to Nov 2023

    Software Developer

    AXA XL, Zurich

    Built a React, Python and SQL decision system in a compliance heavy Swiss enterprise environment.

  • Sep to Oct 2023

    Research Engineer, OCR and automation

    Sulzer, Zurich

    Prototyped OCR and machine learning extraction for graphs and tables from technical documents, and compared rule based, ML and deep learning options with a cost and timeline feasibility analysis.

  • 2021 to 2024

    MSc Data Science

    University of Zurich

    Thesis on high dimensional forecasting, and a Master Project on streaming outlier detection across 1.6M+ data points.

  • 2017 to 2021

    BEng Information Technology

    D. J. Sanghvi College of Engineering, Mumbai

    Coursework in machine learning, software development and cloud computing.

Every change runs a test suite before it lands.

How I work.

I build with AI coding agents under strict gates, which is why one engineer can deliver quickly without guessing.

  • You work directly with me.

    No hand offs

    The person who scopes the problem is the person who builds the fix.

  • Nothing lands untested.

    Gates on every change

    Every change runs a test suite before it lands, and integrations are verified against the live provider APIs.

  • You keep the evidence.

    Written evidence at the end

    Every engagement ends with written evidence your team keeps, so you don’t depend on me afterwards.

What I work with.

Reliability and cost
Budget checks before each call, cost circuit breakers, rate limiting, human approval gates, observability, LLM evaluation
LLM systems
RAG, multi agent systems, query orchestration, streaming, guardrails, MCP, LangChain, LiteLLM, Hugging Face, Bedrock
Cloud and backend
AWS Lambda, API Gateway, S3, DynamoDB, CloudWatch, CDK, FastAPI, Docker, PostgreSQL, CI/CD
Languages and research
Python, TypeScript, SQL, Go, Rust, PyTorch, anomaly detection, time series forecasting

KazenAI is a product, not a consulting service.

KazenAI is the product I built from this work. Clients can use it; it’s never required. Under the engagement agreement, what I build for you is yours, KazenAI stays mine, and your code, systems and confidential data never go into it.

Tell me what you’re trying to put in front of customers.

The first 30 minute call is free, and I reply within one business day.

Tell me what’s blocking you

[email protected] LinkedIn GitHub KazenAI