Work · Full detail · status: online

Work

Staff Software Engineer with 16+ years across AI agent platforms, frontend, and backend. Founded ServiceNow's Agentic Developer Platform, led a 9-person team, and ships agent systems end-to-end: tool orchestration, eval-gated rollout, governance, and full-stack React/Java ownership.

What I do

Agentic AI & MCP

Designed and shipped MCP-driven agentic workflows integrated into the engineering lifecycle, adopted by 20+ teams with roughly 95% less research and debugging effort.

MCP, Claude Code, Build Agent, Tool orchestration, Self-healing loops

Local LLM inference

Run MLX-optimized models (Qwen, Gemma, DeepSeek) locally on Apple silicon via Ollama, plus memory-efficient loaders like turbo-fieldfare that stream model portions on demand: Gemma 4 26B under 2GB RAM. Took VLMs end-to-end on-device: Qwen2-VL-2B on llama.cpp/GGUF via Metal across a quantization ladder on iPhone, with sub-second TTFT from architecture and resolution levers.

Ollama, MLX, turbo-fieldfare, Apple silicon, Memory-efficient inference, llama.cpp, GGUF quantization, On-device inference

Developer platforms

Founded the Agentic Developer Platform: multi-team bootstrap and governance infrastructure for agents, skills, and MCP servers.

Multi-team, Governance, Telemetry

Frontend architecture

Architected scalable React and TypeScript systems powering low-code tools like Table Builder and Workspace Builder.

React, TypeScript, Low-code

Backend & data ownership

Hands-on backend behind the surfaces: Python/FastAPI and SQLite services with guarded, read-only SQL access, plus Java/Glide enterprise case backends and REST APIs.

Python, FastAPI, SQLite, Java / Glide, REST APIs

System design

Metadata-aware, multi-model architectures and design patterns built to hold up across teams, tenants, and releases.

Scalable systems, Design patterns

Quality & reliability

Enterprise testing strategy with Jest, React Testing Library, and Playwright; performance optimization and WCAG/ARIA accessibility. Lifted legacy coverage from 20% to 90%.

Jest, RTL, Playwright, WCAG/ARIA, Performance

Technical leadership

Lead a 9-person engineering team, run technical hiring and high-bar architectural reviews, and mentor engineers in AI-first development practices.

Hiring, Mentoring, Reviews

Agentic Developer Platform

Multi-agent orchestration. 20+ skills, 20+ agents, 20+ teams, four weeks from concept to production.

ADP coordinator multi-agent pattern MCP serverstools and context skills, 20 plusbootstrap agents, 20 plusorchestrated governancetelemetry
One session bootstraps a squad: skills, agents, rules, MCP servers.

Selected work

run 01 · ServiceNow✓ shipped

Agentic Developer Platform (ADP)

Creator, ServiceNow

Multi-team bootstrap and governance infrastructure for Claude Code, MCP servers, agents, and skills. Built in four weeks on a multi-agent orchestration pattern, rolled out to 7 pilot squads across 20+ teams with 20+ skills and 20+ agents.

✓ −90% task resolution time
✓ 20% → 90% legacy coverage
✓ open defects → single digits org-wide
✓ Days → hours
✓ Multi-agent pattern
run 02 · ServiceNow✓ shipped

MCP-driven engineering workflows

20+ teams, ServiceNow

Integrated MCP-driven agentic workflows into the engineering lifecycle organization-wide. Reduced research and debugging effort by approximately 95% while improving accuracy.

✓ −95% research & debugging
✓ 20+ teams
✓ Higher accuracy
run 03 · ServiceNow✓ shipped

Build Agent, ServiceNow Studio

App Engine, ServiceNow

Elevated App Engine with agentic workflows for AI-assisted application creation, flow generation, and tool orchestration across 35+ metadata types and 11 domains. Built on the planning pattern (think first, then execute) with a metadata-aware, multi-model (Claude default; Now LLM + Claude on Bedrock), self-healing agentic architecture.

✓ 35+ metadata types · 11 domains
✓ Multi-model
✓ Self-healing
✓ Metadata-aware
✓ Planning pattern (think → execute)
run 04 · ServiceNow✓ shipped

Release lifecycle & app summary agents

Now Assist for Creator, ServiceNow

Automated delta analysis, human-readable release notes, and CAB-ready deployment manifests: documentation time from hours to a single click. Built on the REAct agentic framework (reason → act → observe). Ships as the Release lifecycle documentation agent in Now Assist for Creator.

✓ Hours → one click
✓ CAB-ready manifests
✓ Delta analysis
✓ REAct framework
Telemetry

Results

Every number below is sourced from the work it describes.

95%
less research and debugging effort for 20+ teams on MCP workflows (measured across the 7 pilot squads in the 4-week rollout)
−90%
case task resolution time on the Agentic Developer Platform
20% → 90%
legacy test coverage lift on ADP pilot squads
single digits
open external defects org-wide, down ~90%
80% → 95%
accessibility compliance lift, Angular-to-React migration at Reputation
9
engineers led and mentored as tech lead at ServiceNow
4 wks
from concept to production for a multi-team AI platform
80%
faster test-to-production HRMS setup, Oracle Benefit Plan Copy
30s → 805ms
TTFT for on-device VLM inference via architecture and resolution levers (Ordo)
Lab

On-device, on-desk

# desk: Apple silicon
$ ollama run qwen3 && turbo-fieldfare load gemma-4-26B
✓ 26B under 2GB RAM (streamed on demand)
# phone: iPhone A16, Qwen2-VL-2B, GGUF ladder, 270 runs
$ ordo bench --ladder q4_k_m..q2_k --device a16
✓ TTFT 30s to 805ms (architecture and resolution levers)
Builds

Everything shipped

Every live build, with what each one changed. The home page shows a hand-picked four.

SpendIQ Copilot

Agent · on home

14-case golden-set eval harness passes with majority voting: agent answers enterprise data questions without inventing numbers

Conversational spend-analysis agent: LangGraph ReAct over SQLite + FTS5 with SQL guardrails (SELECT-only, read-only connections), an AST-whitelisted calculator instead of eval, and a 14-case golden-set eval harness with majority voting, all passing

ordo

iOS app · on home

Time-to-first-token cut from 30s to 805ms on an iPhone A16 by changing architecture and resolution, not hardware

On-device vision-language model built on Qwen2-VL-2B with llama.cpp across a GGUF quantization ladder, deployed to iPhone (A16), with a private photo eval set, per-stage TTFT decomposition, and LoRA accuracy recovery

Revision

Desktop app · on home

Principal-level interview prep that works fully offline from a single SQLite file: no account, no sync, no network

Local-first Tauri desktop app for principal-level interview prep: FSRS-5 spaced repetition, drag & air gestures, single SQLite file, fully offline. DSA / system design / AI / behavioral decks with glassmorphic review, cloze + KaTeX, and 53-week analytics

Switchyard

Simulator · on home

Every internal step of an agentic RAG loop (ingestion, retrieval, tool calls, memory) is watchable instead of imagined

Interactive simulator for an agentic AI + RAG pipeline: watch ingestion, retrieval, tool calls, memory, and a live trace of every internal step while the loop runs.

jev-browser

Library

One observed element and one operation per browser step, with zero runtime dependencies and no screenshots in the loop

Harness-agnostic TypeScript core that puts Jev (TypeSafe System One) in charge of browser decisions: one observed element and one operation per step, text-only payloads with no screenshots in the loop, zero runtime dependencies

job-search-skills

Agent skills

A whole job search (sweep, rank, autofill, submit) runs locally against the real eligibility rules

Two portable agent skills that run an entire job search locally: job-finder sweeps boards and ranks roles by real eligibility, apply-to-jobs autofills and submits ATS applications in your own browser, and a Jev decision layer keeps uncertain answers uncertain

intent

Protocol

Agent-driven changes ship with declared scope, protected tests and a green baseline enforced by a verifier

Repo-owned protocol and verifier for agent-driven changes: declared scope, protected tests, digest-bound approvals, and a green baseline

job-radar

Data pipeline

Senior+ India engineering roles land on a static site with JSON/RSS feeds, with zero runtime dependencies

Daily crawl of senior+ frontend and AI engineering roles in India from company ATS boards into a static site with JSON/RSS feeds; zero runtime dependencies, forkable configuration

tutor

Agent skill

Tutor state on disk survives a clean context, so difficulty tuning carries across sessions

Adaptive tutor skill for AI coding agents: one question per turn, difficulty tuned to the learner, state on disk that survives a clean context

Discontinued: selftest.in · lifetimetax.vercel.app · airoadtripplanner.vercel.app · faang-cv.vercel.app · uberpro.in · swechhafarms.com · covid19open.in · selftest.app

Experience

ServiceNow

Staff Software Engineer
Hyderabad, Oct 2023 to Aug 2026
  • Designed ALA's agent architecture (tool contracts, delta-analysis flow); owned requirements → EA Mar 2026 → GA Apr 2026.
  • Set the App Summary consolidation architecture: Now Assist skills → AI Agent Studio; one generic flow replaces 4-provider settings (Now LLM, Gemini, OpenAI, Anthropic).
  • Drove ADP adoption: legacy test coverage <20% → 95% in 4 weeks across update sets, source control, and team dev; 7 pilot squads.
  • Stabilized Table Builder and Workspace Builder; grew Table Builder entry points 1→4, owned Studio support, UI/API fixes, and frontend performance.
  • Instrumented agent quality in production (reasoning traces, tool-selection/hallucination tracking, cost/latency dashboards feeding evals) and shipped human-gated plan → approve → execute → verify with rollback.
  • Tech-lead 9 engineers: ~60% hands-on coding, PR/architecture reviews, mentoring, cross-team coordination; Java/Glide full-stack ownership.
AI Agents, MCP, Python, TypeScript, React, Node.js, Java

Rippling

Senior Software Engineer
Bengaluru, Oct 2022 to Aug 2023
  • Contributed to frontend infrastructure and global engineering initiatives; drove codebase improvements, interviewed candidates, and mentored junior engineers.
JavaScript, React, TypeScript, Node.js, Python, Playwright, Sentry, LogRocket

Reputation

Lead Engineer
Hyderabad, Sep 2020 to Sep 2022
  • Led the Actions Team frontend, migrating Angular → React and cutting page load time in half.
  • Delivered the Actions feature and management dashboard; raised accessibility compliance from 80% → 95%.
JavaScript, Node.js, React, Python, RTK Query, Sumo Logic

Worktech Software

Co-Founder / Lead Developer
Hyderabad, Jul 2017 to Aug 2020
  • Built products and services with JavaScript, Node.js, MongoDB, Meteor, and REST APIs.
  • flexzone.in (2018–2020): café aggregator for coworking spaces; hospeto.in (2017–2018): doctor video consultations with records and billing.
JavaScript, Node.js, MongoDB, Meteor, REST APIs

Eze Software Group

Senior Developer
Hyderabad, Jun 2016 to Jun 2017
  • Built an order-management system for real-time short-selling, plus EzeLocate and DataFeed for short inventory and real-time stock data (REST APIs, MS SQL).
REST APIs, MS SQL

Oracle

Project Leader
Hyderabad, Jun 2010 to May 2016
  • Built Plan Copy and Benefits Relationships systems (Java, Oracle Database, SQL/PLSQL); cut HRMS test-to-production data setup by 80%.
Java, Oracle Database, Oracle ODI, SQL/PLSQL

Skills

AI & Agentic Engineering

AI agents, Agent UIs, MCP workflows, Claude Code, LLM APIs (Anthropic, OpenAI, Gemini), LangChain / LangGraph, Prompt engineering, Tool orchestration, Multi-model systems, Multi-agent orchestration, REAct agents, LLM evals (golden sets, LLM-as-judge), Agent evaluation & guardrails, Human-in-the-loop agent design (plan → approve → execute → verify), AI governance (AI Agent Studio / Control Tower), RAG / keyword retrieval (BM25, FTS5)

Frontend & Platform

JavaScript (ES6+), TypeScript, React, Next.js, Redux Toolkit, RTK Query, Node.js, Webpack, Vite, PWA

Backend & Data

Python, FastAPI, SQLite, MySQL, Java, REST / GraphQL APIs, MongoDB

Architecture

System design, Scalable frontend architecture, Design systems & component libraries, Developer productivity, Metadata-driven development

Reliability & Quality

Jest, React Testing Library, Playwright, Performance optimization, Performance profiling & tuning (production regressions, budgets), WCAG / ARIA accessibility

CI/CD & Tooling

GitHub Actions, Jenkins, Docker

Observability

Sentry, LogRocket, Datadog, Sumo Logic, Agent observability (reasoning traces, tool-selection errors, cost/latency), On-call & incident command

Education

National Institute of Technology (NIT), Tiruchirappalli

Master of Computer Applications (MCA), 2007-2010

Banaras Hindu University (BHU), Varanasi

BSc (Hons), Mathematics, 2003-2006

Patent US20150046358

Importing tested objects into benefits programs deployed on production systems. Assigned to Oracle Corp., status Abandoned. Google Patents