Writings
Thoughts on systems architecture, AI engineering, team building, and delivering outcomes that matter.
2026
AI Agent Safety Governance: An Engineer's 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
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
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
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
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
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
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
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
How to manage LLM provider risk in regulated industries. Trust Boundaries Model, multi-provider strategy, fallback patterns, and compliance mapping for financial services AI.
2025
Remote-First Engineering Teams: Building Distributed Organizations That Deliver
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
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
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
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
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
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
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
Dipankar Sarkar explains how to use AI code generation in production systems. The Vibes Inside Guardrails framework for capturing AI productivity while maintaining reliability.
2024
Optimizing ARM Builds in CI/CD: Emulation, Native Builds, and Cloud-Native 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
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
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
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
Dipankar Sarkar built Nykaa's real-time data ingestion framework processing 5B+ daily events using AWS Lambda and Apache Flink, enabling data-driven personalization.
2023
RoboGPT: Natural Language Robot Programming and 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
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
Dipankar Sarkar built Nykaa's integrated ad platform and social commerce solution, achieving 200% revenue increase and onboarding 1000+ influencers.
2022
2021
Building Scalable E-Commerce Infrastructure: Platform Migration and High-Performance Services
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
Dipankar Sarkar built analytical systems at Tyroo (India's largest AdTech company) processing 10B+ daily ad impressions using Core Java for real-time insights.
2020
2012
Shaping the Future of Content Sharing: Early Days at 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
Dipankar Sarkar built PHIRE at MPower Money - the world's first mobile debit network enabling SMS-based banking for unbanked populations using Python.
2011
2010
Optimizing Vision Algorithms: My Research Experience at B-Core Software in 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
Dipankar Sarkar developed a Web Service PDS plugin for Oracle Reports during internship at Oracle Corporation, receiving recognition from US headquarters.