Expertise

I’d rather show you a short, honest list of things I’ve actually shipped than a long one of things I’ve heard of. Here’s where I’m genuinely useful.

Generative AI & Agentic Systems

This is most of my work right now. Not chatbots. Systems that do things and improve on their own.

Self-learning agents. At Comify I built a copywriting agent that researches a brand’s domain, applies psychological triggers to draft message templates, then keeps optimizing them against live click-through data. It gets better at a brand the longer it runs.
Multi-agent orchestration at scale. The Comify platform is a fleet of agents and 50+ Lambda functions coordinating to deliver 50M+ messages a day, deciding audience, channel, content, and timing.
Image & video generation pipelines. Product-photoshoot engines that turn a single product shot into on-brand campaign creatives in bulk, using vision LLMs (Gemini, Claude) and diffusion tooling (Stable Diffusion, ComfyUI). At Lenskart this took catalogue photoshoot coverage from 73% to 100% in a month.
Recommendation systems. Clickstream-driven recommenders (recently-viewed, popular, demography-based) that lifted revenue on targeted communication workflows by 60–80% over untargeted sends.
RAG and retrieval where it earns its keep, and not where it doesn’t.

Five years of getting models to run fast, on real devices, in real lighting.

Virtual try-on at consumer scale. Eyeglass AR try-on delivered to millions across Android, iOS, and web; ~9% lift in online revenue since launch.
Real-time, on-device CV. Eyeglass removal on the live AR video feed at 12+ FPS on an iPhone 12, so existing spectacle wearers could actually see themselves in new frames. Edge inference, tight frame budgets, no round-trip to a server.
Try-on beyond glasses. Contact-lens try-on for the Aqualens sub-brand (20%+ sales lift in markets like the UAE), and a real-time 2D image try-on shipped in a week that replaced a vendor and saved ~$800k a year in licensing.
3D asset pipelines. Rebuilt Lenskart’s 3D try-on pipeline with Blender automation and purpose-built QA tooling: coverage from 65% to 92% in three months, asset development time down ~30%.

Before AI was my job, this was. It still underpins everything I build.

Serverless at scale. A backend of 50+ production AWS Lambda functions orchestrating 50M+ daily messages, designed, deliberately, around minimizing cost per message.
Distributed telephony. CODAC peaked at 10M+ calls a day across 10+ telephony servers (PHP → Python, MySQL, Redis/Memcached) and generated ~$12M a year with a three-person team.
High availability by design. Multi-server, load-balanced, fault-tolerant clusters spanning 100+ servers at 99.9% uptime, with custom tooling for the genuinely hard parts, like distributing phone numbers across servers without collisions.
The unglamorous foundations. Monitoring, release planning, capacity, and the alerting that lets a small team sleep.

I’ve built two teams from one person, and led an org of thirty.

Team building & retention. Grew Lenskart’s AI/AR/Data team from 1 to 12; led a 30+ person engineering org at MyOperator with the company’s lowest attrition.
Build-vs-buy & vendor strategy. The calls that quietly save the most money usually aren’t about technology at all.
Working with founders & product. Roadmap and ideation directly with co-founders and senior product leadership, translating between “what’s possible this quarter” and “what the business actually needs.”
Agentic engineering practice. Using AI tooling to accelerate the team’s own delivery without trading away reliability.

If one of these is the problem you’re staring at right now, let’s talk.