• Analysing Tracxn's AI Assistant logs daily for output quality, usage and cost, tracking the input and output tokens behind every turn, and optimising prompts, context and token use to cut cost and response times.
• Adding skills and new capabilities from across the Tracxn platform for the assistant to use, and checking tool behaviour to keep output quality high.
• Running POCs for new assistant features and new models, with evals comparing quality, latency and cost against the current setup, and taking feature, model and router-model changes from proposal through review to rollout.
• Built an internal MCP server from scratch, wiring Tracxn workflows into VS Code, Cursor, Claude, Codex, and ChatGPT for AI-assisted scripting, legacy API migration, and conversational access to API schemas, filters, sorting options, and response structures.
• Built a custom GPT on the ChatGPT platform and the MCP server tools behind it, so Tracxn data can be searched and queried conversationally.
• Designed and built a full-stack CMS with a WYSIWYG editor, live preview, role-based access, and UI visibility controls - removing engineering dependency for docs updates.
• Architected a full-stack CRM pipeline (Trello-like): multiple workspaces, configurable lists, fine-grained role-based access, drag-and-drop cards, real-time collaboration over WebSockets, bulk ingestion from CSV, email and platform links, workspace export, and activity tracking.
• Migrated every internal and external user off the legacy Reflux-based pipeline, 60-70% faster and carrying custom entities beyond companies.
• Built an internal recruitment tool covering job postings, applicant tracking, and hiring pipeline management.

Promoted to Senior Software Engineer from Software Engineer.

Vercel AI SDK, MCP, TypeScript, Next.js, React.js, Node.js, Express.js, MongoDB, AWS (Lambda, S3, CloudWatch, CloudFront), Redux, React Aria, Puppeteer

• Delivered full-stack features across React and Node/Express with clean architecture and reusable modules, boosting developer velocity by 70%.
• Built configurable personalization and targeting modules for discovery and relevance, lifting user adoption by 60%, and led delivery across dashboard and search workflows, lifting engagement by 70%.
• Cut page load time and TTI by 75% via bundle splitting, render tuning, and component refactors.
• Deployed AWS Lambda serverless export pipelines for report generation, eliminating idle compute and scaling throughput by 70%.
• Built an A/B testing framework and feature flag system for safe rollouts, reducing regressions by 50% and making product decisions data-driven.
• Raised accessibility (WCAG) across core workflows with React Aria, hardened services with optimised queries and caching, and strengthened observability with dashboards and alerting.
• Mentored junior engineers and partnered with Product, Design, and Data to improve delivery predictability and code quality.

JavaScript, TypeScript, React.js, Next.js, Node.js, Express.js, MongoDB, AWS (Lambda, S3, CloudWatch, CloudFront), Redux, React Aria, Git/GitHub, Postman

• Mentored 500+ students across 15+ full-stack cohorts on MERN stack, design patterns, and best practices.
• Led code reviews and guided production-grade project builds, raising architectural rigor across cohorts.
• Ran DSA and problem-solving sessions to strengthen algorithmic thinking and interview readiness.
• Provided career guidance and feedback, helping students ship deployable applications and portfolios.

HTML, CSS, JavaScript, React.js, Node.js, Express.js, MongoDB, Git/GitHub, Postman

Intensive full-stack bootcamp covering JavaScript, React, Node.js, MongoDB, data structures, and system design.

Sikar, Rajasthan.