Agentic AI Engineer · Revenue Automation Architect
Full-stack agentic AI systems that replace manual GTM and RevOps work — not chatbot demos. I build the agents, automations, CRM integrations, and cloud infrastructure teams actually run in production.
Shipping systems that survive production.
From interfaces to infrastructure and data flows.
Open to professors, labs, universities, and technical writing.
Helping founders and leaders make architecture decisions faster.
Raising engineering standards through reviews, systems thinking, and guidance.
Turning messy, ambiguous problems into systems that ship.
Built Across Domains
About
I build the software and the agents that run on top of it. That means full-stack product work, CRM and GTM automation, the cloud infrastructure underneath — and, on the research side, quantitative finance.
5+
Years shipping
9
Roles
20+
Articles
A demo runs on data someone cleaned first. Production runs on duplicate accounts, half-filled fields, and a rep who typed the deal name three different ways. I build for the second one — which mostly means deciding what the system does when it is not confident, rather than assuming it always will be.
Shipping a feature and moving a number are different jobs. Automation that saves twelve hours a week is worth nothing if those hours were never the constraint, so I start from the metric the team is actually judged on — pipeline, conversion, cost per outcome — and work backwards to what the software has to do.
Agents, workflow automation, CRM integration, agent-FTE systems, and the cloud delivery underneath them. The hard part is almost never the model — it is the boundary: which decision the agent owns outright, which one it escalates, and what it is allowed to touch while nobody is watching.
I am working toward a PhD alongside the day job, in AI and quantitative finance. The research reading changes how I build: it is where the habit of stating a hypothesis before running the experiment comes from, which turns out to matter more in production than it does on paper. Open to labs, supervisors, and collaborations.
Most of the leverage in a small team is not in the code. It is in whether the next engineer can read the decision you made six months ago and know why. Hiring input, code review habits, architecture reviews, and the occasional blunt second opinion for a founder about to commit to an expensive bet.
An agent that nobody measured is a rumour. I set the success and escalation criteria before rollout, so there is a real answer to whether it worked rather than an argument about it six weeks later.
Eight published packages, twenty-odd technical write-ups, and profiles that update themselves. None of it is self-promotion for its own sake — it exists so that anyone deciding whether to work with me can check the work first and arrive at the conversation already knowing the answer.
Selected Milestones
Every item here links out to the record behind it: the scholarship, the contest leaderboard, the package on npm, the issued credential. Check any of them.
Public Milestone
GitHub / npm / PyPI / LeetCode / Medium
Public Milestone
Springer Nature / Mehran University Research Journal
Program Selection
WorldQuant University
Skill Proof
Harvard CS50x
Career Journey
Nine roles, starting in frontend and ending up owning AI-enabled platforms end to end. The hackathons and the research work happened alongside the day job, not instead of it.
VentureDive
Jul 2026 – Present
Dunzo
Jun 2026 – Present
WorldQuant University
Sep 2025 – Mar 2026
Valar Institute
Mar 2025 – Present
Digital Dividend Global
Nov 2023 – Jun 2026
Services
Six lines of work, one throughline: systems that run without someone babysitting them. Agents and GTM automation sit at the front. Cloud, fintech, and Web3 engineering sit underneath.
RevOps
GTM &
2-6 weeks for pilot automation to production rollout
Service
Platform Modernization
2-6 weeks for focused modernization and workflow uplift
Swipe service lanes
01—09Focused starting points
Selected Work
Case studies drawn from production systems
5 shipped projects
A final-year project exploring smart tokens that enable buying, selling, lending, and time-bound trading of gaming assets with profit-sharing mechanics.
Domain
Gaming x Web3
Focus
Tokenized ownership
Stack
Smart contracts + web app
Stack
Migrated notification workflows to SQS, Lambda, and Firebase while improving backend reliability and pushing a large JavaScript codebase toward TypeScript and server-compatible React patterns.
Migration
180K lines affected
Delivery
Realtime + scalable
Stack
SQS / Lambda / Firebase
Stack
Modernized a legacy codebase into a clearer monorepo and microservice setup using Yarn workspaces, Turborepo, Docker, AWS SAM, and stronger development standards.
Setup time
80% faster
CI/CD
15 min saved
Scope
Platform modernization
Stack
Assistants that query backend systems, databases, and user-defined workflows, kept inside explicit operational constraints instead of improvising.
Capability
DB-aware workflows
Mode
Autonomous assistance
Focus
Grounded responses
Stack
Responsive web, mobile, and backend systems for a vehicle marketplace serving consumer and business traffic across products, services, and wholesalers.
Audience
100K+ users
Channels
B2C + B2B
Platforms
Web + mobile
Stack
Small, boring, useful. Packages on npm and PyPI that solve a problem I hit once and did not want to hit twice, published so nobody else has to solve it either.
Certificates prove you sat an exam, not that you can build. These are here because they are verifiable — Credly-issued, leaderboard-ranked, or scholarship-funded — so you can confirm them without taking my word for it.
1 course · 7 certifications · 500+ problems solved
Competition
HeimdallAI
Prototype submitted · Deriv AI Talent Sprint
Competition
Hermes Nexus Enhanced Product Vision
Hackathon / challenge submission · AI Agent innovation sprint
Competition
CALICO Fall '25
22nd / 538 nationally · CALICO Fall '25
Certification
Foundations of Financial Engineering
WorldQuant University
Certification
Set Up a Google Cloud Network Skill Badge
Google Cloud
Certification
Optimize Costs for Google Kubernetes Engine Skill Badge
Google Cloud
Written after shipping the thing, not before. Next.js performance, production AI, cloud trade-offs, and the calls that turned out to be wrong.
Capabilities
Nothing listed here is aspirational. Each tool below has shipped in something a client or an employer paid for, and each one links through to the service line and the case study it came from.
Collaborator Feedback
Quotes are the weakest form of proof, so treat these as context. The case studies and the public code are what to actually check.
Tell me what is actually broken — the bottleneck, the workflow, the research question. You will get a straight answer about whether I am the right person, including when I am not.
Email or share a focused project brief
