dhairya.patel
Open for collaboration

Portfolio · 2026

Dhairya Patel

AI Engineer · Tech Lead · ex-Startup CTO

I build AI-native products end-to-end — and ship them fast.

010+years shipping products
0224 / 7autonomous agents in production
030%of my workflow automated
040 1end-to-end ownership
Scroll
01

About

sys / operator

I ship the whole thing — backend, frontend, infra, and the AI layer on top.

AI Engineer and ex-startup CTO — I take products from zero to one and own them end-to-end. I co-founded Quido (0 → 5,000+ users), shipped production autonomous agents at Valory, and now lead engineering at Spocket. I work AI-native: my own toolchain of skills, hooks, and subagents clears the drudgery, so shipping fast is the default — not the exception.

02

Ask my AI

concierge / on-device

I build agents for a living, so my portfolio has one. It answers the questions a hiring manager actually asks — try one below.

Concierge dhairya · v0.1
Concierge I'm the concierge for this portfolio. Ask me about Dhairya's work, or pick a question below.

Offline · answers on-device · no data leaves your browser

03

Experience

log / 2019 - now

select an entry to expand

tech lead · jun 2026 - now

  • Directed org-wide security remediation - 35,000+ alerts across 100+ repos cleared in ~2 weeks via an AI-driven framework - then stood up a vulnerability-management program adopted org-wide.
  • Took ownership of AWS infrastructure across services; led a cost-optimization initiative and standardized deployments for reliability.
  • Built an AI-native development workflow and shared it across the team to speed up delivery.
  • Primary engineering owner for production escalations - partnered with Customer Success to cut resolution times.

full-stack engineer · jun 2025 - 26

  • Shopify embedded apps end-to-end: AI automation, Cash-on-Delivery, subscription billing.
  • Designed a unified credit system; built SEO Audit + One-Tick Upsell.
  • Launched a production Shopify app with Stripe billing through Shopify review.
  • Delivered a production Telegram AI personal assistant solo for a client - end to end, on the Hermes framework.
  • Led Polystrat (autonomous trading agent on Polymarket) from research and strategy through deployment, with a self-improving accuracy loop.
  • Implemented asset whitelisting on Optimism for Optimus (showcased at ETHCannes) and secure, smart-contract-backed withdrawals for Optimus/Modius.
  • Optimized concentrated-liquidity allocation (EMA look-back tick selection); built a trailing stop-loss safety exit.
  • Fixed critical parallel-execution bugs and built the agent reporting/analytics system.
  • Every agent settled its calls via x402.
  • Led an internal Ranges & Styles platform that streamlined workflow management for faster client approvals.
  • Built a unified sampling + order-tracking system with automated client email updates for real-time visibility.
  • Engineered the raw-material sampling workflow - more transparency in procurement and better operational planning.
  • Shipped an AI fault-detection workflow on live factory camera feeds to catch design flaws and cut manpower cost.
  • Platform features that lifted design-team throughput +30% - more styles shipped per week.
  • Users invest in expert-curated strategies by linking their existing exchange wallet.
  • Scalable backend (FastAPI + Spring Boot + AWS) with real-time market data and automated portfolio rebalancing on strategy/volatility changes.
  • React Native mobile + React/Next.js web for a smooth cross-device experience.
  • Scaled to 5,000+ users managing $50k+ in assets.
  • Built Orange rental-platform features that raised sales and cut overall checkout time for agents.
  • Implemented map-matching via a Hidden Markov Model - snapping GPS pings to the road to optimize route + trip cost.
  • Designed an in-house referral engine replacing a paid third-party tool, cutting operational cost.
  • Created an in-house reporting + search tool for the relevant team.
  • Built a Django API to train ULMFiT sentiment models and serve predictions (deployed via Apache).
  • Developed the sentiment model for a vernacular-language chatbot - 93% accuracy.
04

What I can ship

offer / outcomes

Not a service menu — things I've already shipped and can own end-to-end. Each one is backed by real work, not a promise.

01

Production AI agents

Autonomous agents that act safely when the stakes are real - exactly-once execution, fail-closed actions, and self-improving accuracy loops. The hard 20% most demos skip.

proof Valory · Vacya

02

0 → 1 products

Whole products from an empty repo to real users - backend, frontend, mobile, infra, and the AI layer on top. Founded, owned, and shipped end-to-end.

proof Quido · Thimblerr

03

AI-native delivery at scale

My own agentic dev layer - skills, hooks, and subagents - that clears the drudgery so the whole team ships faster. 35,000 alerts across 100+ repos, cleared in ~2 weeks.

proof Spocket · Valory

05

Projects

selected work · figs. 05.1 – 05.6

n01 Valory · 2025 - 26 · autonomous trading agent

Polystrat

An autonomous trading agent on Polymarket (Polygon), led end-to-end: strategy design plus a self-improving accuracy loop that scores predictions against real market outcomes and feeds them back. The hard part was the safety layer - exactly-once execution and fail-closed actions.

  • Python
  • Open Autonomy
  • Polygon
  • Agent safety
fig. 05.1 · converge prediction → outcome

n02 Valory · 2025 · on-chain DeFi agent

Optimus

An autonomous DeFi agent managing on-chain positions on Optimism - concentrated-liquidity optimization, asset whitelisting, and fail-closed secure withdrawals with a trailing stop-loss exit. Shipped to production; shown at ETHCannes.

  • Optimism
  • DeFi
  • Open Autonomy
  • Agent safety
fig. 05.2 · range recenter concentrated liquidity

n03 Valory · 2026 · Telegram AI assistant

Assistant

A production Telegram AI personal assistant, delivered solo for a client on the Hermes framework - scoped and architected end-to-end, from first requirements through a live client handover.

  • Hermes
  • Telegram
  • Python
  • Autonomous agent
fig. 05.3 · assist ask → act → reply

n04 Co-founder & CTO · 2022 - 23 · crypto platform

Quido

Users invest in expert-curated strategies by linking their exchange. I built the whole stack - FastAPI + Spring Boot + AWS backend, React Native mobile, Next.js web, automated portfolio rebalancing - and scaled it 0 → 5,000+ users, $50k+ AUM.

  • FastAPI
  • Spring Boot
  • React Native
  • Next.js
  • AWS
fig. 05.4 · invest value ↑ · rebalance

n05 Personal prototype · 2025 · voice AI agent

Vacya

A voice AI ordering agent on ElevenLabs that handles a full drive-through order by voice - upsells, allergies and removals, knowledge-base lookups for availability, and human handoff when it should step aside.

  • ElevenLabs
  • Voice AI
  • Conversation design
fig. 05.5 · voice order → upsell → handoff

n06 Ongoing · agentic dev layer on Claude Code

AI-native toolchain

My own agentic dev layer on Claude Code - custom skills, hooks, and subagents for code review, security review, dependency cleanup, and migrations. At Spocket it cleared a 35,000-alert security backlog across 100+ repos in ~2 weeks.

  • Claude Code
  • Agents
  • Skills & hooks
  • DevEx
fig. 05.6 · hover 35,000 alerts → cleared
06

Skills

manifest / 6 modules

lang07

  • Java
  • Python
  • Node.js
  • Go
  • JavaScript
  • TypeScript
  • C++

backend04

  • Spring Boot
  • FastAPI
  • Django
  • Express

frontend05

  • React
  • Next.js
  • Vue.js
  • React Native
  • Flutter

data06

  • PostgreSQL
  • MySQL
  • MongoDB
  • DynamoDB
  • Redis
  • Elasticsearch

infra09

  • AWS
  • GCP
  • Azure
  • Docker
  • Kubernetes
  • Jenkins
  • Kafka
  • RabbitMQ
  • Celery

ai / ml07

  • Open Autonomy
  • LangChain
  • OpenAI
  • PyTorch
  • Cursor
  • GitHub Copilot
  • Claude Code (agentic dev)
07

Contact

channel / open

Let's build
the real thing.

Open to contract and founding-engineer roles, remote-first. If you're shipping something that matters, I'd like to hear about it.

Book a call 15 min · EU/US friendly · no pitch, just a conversation