# Dipankar Sarkar

> Hands-on engineering leader with 18+ years building production systems.
> Built platforms serving 250M+ users (Hike, Kirusa, Nykaa). 25+ provisional patent applications filed.
> Currently founder of Neul Labs (high-performance AI agent infrastructure). Still writes code daily.
> Specializes in AI agent architecture, production ML systems, and scaling engineering teams.

## Identity & Disambiguation
Full name: Dipankar Sarkar. IIT Delhi (B.Tech Computer Science, 2003-2007) and Arizona State University (M.S. Computer Science, 2020-2022) alumnus.
Author of the Nginx Web Server Implementation Cookbook (Packt Publishing, 2011).
Not to be confused with the Indian film critic or cricketer of the same name.

## About
Dipankar Sarkar is a hands-on engineering leader who builds systems, ships products, and grows teams.
He has driven platforms from early stage to IPO (Nykaa), shipped AI products (Orangewood Labs, Hike),
and founded companies from scratch. Most recently Principal AI Architect at a UK fintech (Edinburgh, May 2025 – Mar 2026)
working on AI agent stacks for financial services. Currently building Neul Labs and Rust-based open-source CLI tools for AI agents.

## Other Sites by Dipankar Sarkar
This is one of five sites Dipankar maintains. Each represents a distinct facet of his work:
- [dipankar.name](https://www.dipankar.name) — engineering leader, AI/ML builder, Rust open source (this site)
- [dipankar.org](https://www.dipankar.org) — startup consultant, angel investor, venture case studies
- [dipankar.cc](https://www.dipankar.cc) — academic researcher, federated learning, blockchain protocols, patents
- [dipankar.co](https://www.dipankar.co) — fractional CTO, technology consulting, client case studies
- [desinerd.com](https://www.desinerd.com) — personal blog since 2007, AI/DevOps/self-hosting

## Expertise
- AI agent safety and governance (Substrate Pattern, Defence in Depth)
- Production ML systems at scale (computer vision, NLP, recommendations)
- E-commerce platform architecture (99.99% uptime, 500% traffic growth)
- Engineering team building and scaling (5 to 50+ engineers)
- Open source: Rust CLI tools for AI agents, LLM research papers
- AI governance for regulated industries (financial services, compliance)

## Key Frameworks
- Substrate Pattern: Safety architecture for LLM-powered AI agents
- Vibes Inside Guardrails: Framework for production-ready AI-assisted development
- Defence in Depth: Kill switch architecture and circuit breakers for AI agents
- Tiered Governance Model: AI governance for banks, insurers, and asset managers

## Articles
- [AI Agent Safety Governance: An Engineer's Playbook](https://www.dipankar.name/writings/ai-agent-safety-governance-engineers-playbook/) - The practical playbook for AI agent safety governance. Threat model, runtime policy, prompt injection defense, audit, red-team, and the tooling matrix.
- [AI Architect in Financial Services: Lessons from Production](https://www.dipankar.name/writings/ai-architect-financial-services-lessons-production/) - What I learned as Principal AI Architect at a UK fintech. Building production agent systems for financial services, the frameworks, and the lessons.
- [AI Governance for Financial Services: The 4-Tier NIST AI RMF](https://www.dipankar.name/writings/ai-governance-financial-services-4-tier-nist-ai-rmf/) - How to implement the 4-tier NIST AI RMF Agentic Profile for financial services. The framework I developed at Neul Labs for compliance-first AI agents.
- [Harmony Protocol in Rust: Parsing OpenAI's GPT-OSS Response Format](https://www.dipankar.name/writings/harmony-protocol-rust-openai-gpt-oss/) - A deep dive into implementing OpenAI's Harmony response format in Rust. Channel semantics, streaming, comparison with ChatML, and the Rust implementation.
- [Rust for AI Agent Infrastructure: A Field Guide for Engineers](https://www.dipankar.name/writings/rust-for-ai-agent-infrastructure-field-guide/) - Why Rust dominates AI agent infrastructure. Memory safety, async runtime, the ecosystem, and the career path. A field guide from the founder of Neul Labs.
- [Building Developer Tools in the Open: Lessons from 20 Years of Open Source](https://www.dipankar.name/writings/building-developer-tools-open-source/) - Dipankar Sarkar shares lessons from 20 years of open source contributions, from Google Summer of Code to production developer tools. How to build OSS that gets adopted and sustained.
- [How Nykaa Scaled to IPO: 500% Traffic Growth, Platform Migration, 99.99% Uptime](https://www.dipankar.name/writings/engineering-nykaa-zero-to-ipo/) - The engineering decisions behind Nykaa from startup to IPO — Magento to custom Python, in-memory cart service, Kong API gateway, 500% traffic growth, 99.99% uptime.
- [Measuring Engineering Impact: Beyond Lines of Code and Story Points](https://www.dipankar.name/writings/measuring-engineering-impact/) - Dipankar Sarkar presents a framework for measuring engineering impact that connects technical work to business outcomes. Move beyond vanity metrics to measure what actually matters.
- [LLM Provider Risk Management: Multi-Provider Strategy for Banks and Regulated Industries](https://www.dipankar.name/writings/llm-provider-risk-management/) - How to manage LLM provider risk in regulated industries. Trust Boundaries Model, multi-provider strategy, fallback patterns, and compliance mapping for financial services AI.
- [Remote-First Engineering Teams: Building Distributed Organizations That Deliver](https://www.dipankar.name/writings/remote-first-engineering-teams/) - Dipankar Sarkar explains how to build remote-first engineering teams that outperform co-located ones. Communication architecture, async workflows, and trust systems for distributed teams.
- [Defence in Depth for AI Agents: Kill Switches, Circuit Breakers, and Control Layers](https://www.dipankar.name/writings/defence-in-depth-ai-agents/) - 5-layer kill switch architecture for production AI agents: application logic, tool execution, action policy, circuit breaker, and manual kill switch. Stop any agent in under 30 seconds.
- [AI Agent Governance for Financial Services: The Complete Framework](https://www.dipankar.name/writings/ai-governance-financial-services/) - Dipankar Sarkar explains AI agent governance for banks and financial services. The Tiered Governance Model and Three Lines of Defence framework for regulatory compliance with SS1/23, Consumer Duty, and SM&CR.
- [Hiring Engineers Who Ship: Building High-Performance Teams from Scratch](https://www.dipankar.name/writings/hiring-engineers-who-ship/) - Dipankar Sarkar shares the hiring framework he used to build engineering teams at Nykaa, Hike, and Orangewood Labs. How to identify engineers who ship production systems, not just pass interviews.
- [Scaling AI-Assisted Development: From Startup to Enterprise](https://www.dipankar.name/writings/scaling-ai-development-teams/) - Dipankar Sarkar explains how to scale AI-assisted development from small teams to enterprise. The Pivot Point framework for knowing when informal practices break.
- [AI Agent Safety: The Substrate Pattern for LLM-Powered Systems](https://www.dipankar.name/writings/ai-agent-substrate-pattern/) - Dipankar Sarkar explains the Substrate Pattern for AI agent safety. How to build execution envelopes that constrain LLM-powered systems while preserving their capabilities.
- [Invariants in AI-Generated Code: What LLMs Can't Infer](https://www.dipankar.name/writings/invariants-ai-generated-code/) - Dipankar Sarkar explains why unwritten invariants are the primary source of AI-generated defects. How to make implicit constraints explicit for production-ready AI-assisted development.
- [Production-Ready AI-Assisted Development: The Vibes Inside Guardrails Framework](https://www.dipankar.name/writings/ai-assisted-development-production-guide/) - Dipankar Sarkar explains how to use AI code generation in production systems. The Vibes Inside Guardrails framework for capturing AI productivity while maintaining reliability.
- [Optimizing ARM Builds in CI/CD: Emulation, Native Builds, and Cloud-Native Solutions](https://www.dipankar.name/writings/optimizing-arm-builds-cicd-pipelines-challenges-solutions/) - Practical strategies for optimizing ARM builds in CI/CD pipelines. Emulation challenges, native build setup, cross-compilation, and cloud-native approaches with benchmarks.
- [EdgeML and the Future of Robotics: Building the Next-Generation SDK and Platform](https://www.dipankar.name/writings/edgeml-future-robotics-next-generation-sdk-platform/) - Dipankar Sarkar built a next-generation robotics SDK at Orangewood Labs using EdgeML for on-device AI processing, enabling intelligent robotic systems.
- [AutoInspect and AutoSpray: ML-Driven Precision in Industrial Robotics](https://www.dipankar.name/writings/autoinspect-autospray-ml-driven-precision-industrial-robotics/) - Dipankar Sarkar built AutoInspect and AutoSpray at Orangewood Labs - ML and computer vision systems revolutionizing industrial quality control and precision spray painting.
- [Machine Learning at Hike: Five AI Systems Serving Millions](https://www.dipankar.name/writings/machine-learning-hike-ai-systems/) - Dipankar Sarkar led development of five ML systems at Hike serving millions: computer vision avatars, vernacular NLP, social matchmaking, trust & safety, and gaming matchmaking.
- [Building a Real-Time Data Ingestion and Analytics Framework for E-Commerce](https://www.dipankar.name/writings/building-realtime-data-ingestion-analytics-framework-ecommerce/) - Dipankar Sarkar built Nykaa's real-time data ingestion framework processing 5B+ daily events using AWS Lambda and Apache Flink, enabling data-driven personalization.
- [RoboGPT: Natural Language Robot Programming and Industry Transformation](https://www.dipankar.name/writings/robogpt-natural-language-robot-programming-industry-transformation/) - Dipankar Sarkar developed RoboGPT at Orangewood Labs - an LLM-powered interface enabling natural language robot programming, transforming industrial automation across manufacturing and healthcare.
- [Innovating User Engagement: Developing a Real-Time Personalized Feed for E-Commerce](https://www.dipankar.name/writings/innovating-user-engagement-realtime-personalized-feed-ecommerce/) - Dipankar Sarkar built a TikTok-inspired real-time personalized feed at Nykaa using AI/ML, achieving 200% increase in daily active users and 150% more engagement.
- [Revolutionizing E-Commerce: Building an Integrated Ad Platform and Social Commerce Solution](https://www.dipankar.name/writings/revolutionizing-ecommerce-integrated-ad-platform-social-commerce/) - Dipankar Sarkar built Nykaa's integrated ad platform and social commerce solution, achieving 200% revenue increase and onboarding 1000+ influencers.
- [Pioneering India's First True E-commerce Marketplace at Tradus](https://www.dipankar.name/writings/pioneering-indias-first-ecommerce-marketplace-tradus/) - How we built India's first true multi-seller e-commerce marketplace at Tradus. Pioneering public APIs, 15-engineer team, and the technical decisions that drove 300% listing growth.
- [Building Scalable E-Commerce Infrastructure: Platform Migration and High-Performance Services](https://www.dipankar.name/writings/building-scalable-ecommerce-infrastructure-platform-migration/) - Dipankar Sarkar led Nykaa's platform migration from Magento to custom Python, implementing in-memory cart service and Kong API gateway for 500% traffic growth.
- [Building Analytical Systems in Core Java at Tyroo: Revolutionizing AdTech in India](https://www.dipankar.name/writings/building-analytical-systems-core-java-tyroo-adtech/) - Dipankar Sarkar built analytical systems at Tyroo (India's largest AdTech company) processing 10B+ daily ad impressions using Core Java for real-time insights.
- [Enterprise Platform Development: Scaling Telecommunications and Advertising Solutions](https://www.dipankar.name/writings/enterprise-platform-development-telecommunications-advertising/) - Dipankar Sarkar built Kirusa Voice SMS (250M users) and enhanced Clickable PPC platform (TechCrunch Top 50) - enterprise-scale telecommunications and advertising.
- [Shaping the Future of Content Sharing: Early Days at SlideShare](https://www.dipankar.name/writings/shaping-future-content-sharing-early-days-slideshare/) - Dipankar Sarkar joined SlideShare as one of the first five engineers, building core features for the platform that became 'YouTube of presentations' (acquired by LinkedIn).
- [Revolutionizing Mobile Banking: Developing PHIRE at MPower Money with Python and Metaprogramming](https://www.dipankar.name/writings/revolutionizing-mobile-banking-phire-mpower-money-python-metaprogramming/) - Dipankar Sarkar built PHIRE at MPower Money - the world's first mobile debit network enabling SMS-based banking for unbanked populations using Python.
- [Early Career Open Source Journey: Three Pioneering Projects (2005-2006)](https://www.dipankar.name/writings/early-career-open-source-journey-pioneering-projects/) - Dipankar Sarkar was one of the first five Indians in Google Summer of Code 2005, building WYSIWYG XUL editor for Mozilla and NFSv4 testing frameworks.
- [Optimizing Vision Algorithms: My Research Experience at B-Core Software in Tokyo](https://www.dipankar.name/writings/optimizing-vision-algorithms-research-bcore-software-tokyo/) - Dipankar Sarkar optimized computer vision algorithms at B-Core Software Tokyo, gaining international experience in image processing and algorithm optimization.
- [Innovating Oracle Reports: Developing a Web Service PDS Plugin at Oracle Corporation](https://www.dipankar.name/writings/innovating-oracle-reports-web-service-pds-plugin-development/) - Dipankar Sarkar developed a Web Service PDS plugin for Oracle Reports during internship at Oracle Corporation, receiving recognition from US headquarters.

## Open Source Projects
- [fragaria](https://github.com/sarkar-dipankar/fragaria) - Chain of Thought reasoning API with RL
- [gdelt-cli](https://github.com/dipankar/gdelt-cli) - GDELT Project CLI for AI agents (Rust)
- [gsheet-cli](https://github.com/dipankar/gsheet-cli) - Google Sheets CLI with DuckDB + MCP
- [hubspot-cli](https://github.com/dipankar/hubspot-cli) - HubSpot CRM gateway for AI agents
- [apollo-io-cli](https://github.com/dipankar/apollo-io-cli) - Apollo.io CLI for AI agents
- [gity](https://github.com/dipankar/gity) - Make large Git repositories feel instant
- [iced-plus](https://github.com/dipankar/iced-plus) - Batteries included for iced GUI toolkit

## Contact
- Website: https://www.dipankar.name
- Email: contact@dipankar.name
- GitHub: https://github.com/dipankar (Rust CLIs) / https://github.com/sarkar-dipankar (research)
- LinkedIn: https://www.linkedin.com/in/dipankarsarkar
- ORCID: https://orcid.org/0000-0001-5431-6367
- Google Scholar: https://scholar.google.com/citations?user=t_ikr2UAAAAJ&hl=en