Ayan Putatunda
Staff Data Engineer. Data platforms for AI, and the agentic systems on top of them.
Pleasanton, CA · 510.488.8555 · ayanputatunda87@gmail.com · ayanputatunda.com · linkedin.com/in/ayanputatunda · github.com/AyanPutatunda
Summary
Staff Data Engineer with sixteen years architecting petabyte-scale data platforms that power production AI. Currently leads AI-readiness for the Zendesk Data Platform: context governance, Model Context Protocol architectures that let agents consume governed enterprise data, and agentic workflows that automate the analytics-engineering lifecycle end to end with a human at every review gate. Keynoted IEEE AIC 2026 and co-authored a vision paper under review at IEEE BigData 2026. Builds and ships full-stack AI products independently at Axiomic AI.
Core skills
- Agentic AI
- Anthropic Claude API, Claude Code, Claude Agent SDK, MCP, LangGraph, Multi-agent systems, RAG and vector search, LLM evaluation
- Data platform
- Snowflake, Snowflake Cortex, dbt, Airflow, Fivetran, BigQuery, Spark, Kimball modelling, Semantic layers
- Languages and cloud
- Python, SQL, Docker, GitHub Actions, GCP, Snowflake Data Cloud
- Leadership
- Technical mentoring, Team building, Stakeholder management, Engineering best practices
Experience
- Lead AI-readiness work for the Zendesk Data Platform: Snowflake Cortex semantic layers and skills-driven agentic data engineering.
- Architected petabyte-scale infrastructure with Fivetran, Airflow, and dbt; 40% better delivery efficiency at 99.9% uptime across 5+ engineering teams.
- Established engineering best practices and mentor engineers on multi-system, long-term projects.
- Led the FDR Sales Data Transformation on Google Cloud: 500K+ unified customer profiles in a BigQuery data lake.
- Batch and streaming ETL frameworks reduced data inconsistencies by 60%.
- Architected the pipeline for a first-in-class supply chain AI platform; TB-scale, 99.9% uptime.
- Built and scaled the data engineering team from 2 to 8 with 100% retention.
- Configurable models and a reusable Airflow framework: implementation time down 50%, development up 60%.
- Multi-channel retail POS data integration (RAYMARK, MSBI, SQL Server) for global retail clients; 99.5% data accuracy with fault-tolerant ETL.
- Automated reconciliation processes eliminated manual validation and reduced errors by 85%.
Selected work
- A governed library of AI skills and sub-agents that automates the analytics-engineering lifecycle across multi-repo dbt and ingestion workflows, with humans in the loop.
- Roughly 2.5× faster time-to-production for analytics work, as presented at dbt Summit 2026.
- Targeting an 80% reduction in manual pipeline development across multi-repository dbt and ingestion workflows.
- Zero-touch detection, root-cause analysis, and auto-remediation of data pipeline failures using the Claude Agent SDK with Snowflake, dbt, and GitHub MCP servers.
- Targeting a 70% reduction in mean time to resolution for pipeline incidents.
- On-call load shifted from log reading to reviewing a proposed fix.
- A unified business vocabulary across 10+ domains, built with dbt metrics and Snowflake Cortex semantic views, so people and agents ask questions in the same words and get the same answer.
- Ad-hoc query requests down 45%.
- Self-serve analytics opened to non-technical stakeholders.
- A vision paper and open-source prototype arguing that agent context should be governed data infrastructure: open files for truth, Git for time, a hash-named evidence folder, one SQLite sidecar for speed, and a token-budgeted serving protocol. Under review at IEEE BigData 2026.
- Vision paper submitted to the 1st IEEE Big Data Workshop on Agentic AI for Big Data (AAI-BD 2026), IEEE BigData 2026. Decision expected October 2026.
- Measured feasibility of the primitives: snapshot commit 155 ms and full sidecar rebuild 0.47 s at 10,000 concepts; point-in-time reads and reverts around 3 to 5 ms; 28 MB total storage.
- The multi-agent repository template every Axiomic AI product is built from: agent prompts, MCP server configs, CI, and deploy wiring. Fork, describe the domain, ship.
- PersonasFlow, EstateVision, and WealthPilot all run on it; each new product started from the same fork.
- Axiomic AI operates as an experimental enterprise: the harness is the company's engineering team.
Research and publications
- Vision Paper: contextctl — Auditable, Open-Source Context Infrastructure for AI Agents. Ayan Putatunda, Suhas Jangoan. 1st IEEE Big Data Workshop on Agentic AI for Big Data (AAI-BD 2026), IEEE BigData 2026. Under review, decision expected October 2026.
- Essential PySpark for Scalable Data Analytics. Technical reviewer. Packt Publishing, ISBN 978-1-800563094. Published
Speaking
- Session, Applied AI Summit, Oct 13–15, 2026. Making a Data Platform AI-Ready.
- Session, dbt Summit 2026, Las Vegas, Sep 15–18, 2026. AI-Powered Data Development: How Agentic SDLC & dbt-MCP Transformed Our Data Engineering Workflow, with Suhas Jangoan.
- Keynote, IEEE 5th World Conference on Applied Intelligence and Computing (AIC 2026), Aug 29, 2026. Unlocking Intelligence through Data.
- Address, University of San Francisco. Guest address to the graduating class, MS in Data Science & AI.
- Podcast, #idataengineer podcast, Feb 5, 2021. Data Engineering Confessions #9.
Community
- Judge, 2nd NextGen Hackathon 2026. ACM Fremont Chapter with the Soft Computing Research Society, Aug 15–16, 2026.
- Mentor, Junior and mid-level engineers moving into data and AI engineering, US and Singapore. 20–30 professionals mentored across enterprises; public live sessions on YouTube, Ongoing.
- Technical interviewer, 50+ technical interviews as a coding assessor. Across enterprises, Ongoing.
- IEEE, ieee senior member (application in progress).
Independent work and teaching
- Axiomic AI (axiomic-ai.com). An experimental enterprise: one person, one agent harness, a portfolio of shipped products. Live products: PersonasFlow, EstateVision, WealthPilot, each built on a shared open-source agent harness.
- Built from Bits (YouTube @ayan-in-tech). Hands-on data and AI tutorials: Claude Code, MCP, agents, dbt, Snowflake. Also on Substack and Medium.
- The Practitioners Pod (YouTube @thepractitionerspod). Conversations with people who ship data and AI systems for a living.
- Built from Bits, learning platform. Under construction.
Education
- Master of Computer Science in Data Science, University of Illinois Urbana-Champaign
- B.Tech in Computer Science and Engineering, West Bengal Institute of Technology