SS· Say hello

Portfolio — 2026 Edition

Shashank
Sekhar VS

AI/ML Engineer / Full-Stack Developer / Product Designer

I build systems that reason, ship the products that run them, and design the interfaces people actually touch. Reinforcement-learning agents, production web platforms, and research-backed UX — under one roof.

View selected work Get in touch →
Shashank Sekhar VS

01 — About

Final-year engineering student working across three disciplines that are usually kept apart: applied AI, production web engineering, and UX research. Currently freelancing as a web developer while leading both the technical and design tracks of my college's department club.

My AI work leans toward systems that don't just predict but act, combining forecasting models with reinforcement-learning agents that make operational decisions. My web work favours Next.js and Supabase, built for real tenants and real traffic, not demos. My design work starts from primary research: surveys, interviews, and usability testing, before a single screen gets drawn.

But more than any one discipline, what I love is building: taking a rough idea and pushing it all the way to something real that people can open, click through, and actually use. That moment when a feature finally works exactly as imagined never gets old, and it's the reason I keep choosing projects that ship rather than projects that stay theoretical.

02 — Selected Work

Things I've shipped

01

Hybrid AI Framework for Predictive & Adaptive Supply Chain Management

A hybrid system combining CatBoost regression with a PPO reinforcement-learning agent to run e-commerce supply chain operations. CatBoost forecasts demand, profit, delivery time and late-delivery risk; those forecasts become state inputs for an RL agent that adaptively controls inventory, order prioritization, and delivery scheduling via reward-based feedback. Evaluated on the DataCo Smart Supply Chain dataset (~180K records): mean reward of +222.24 vs. −120.5 for the baseline, with strong RMSE, MAE and R² across every prediction task.

CatBoostPPO / RLPythonTime-series
View project →
02

FlowForge — Autonomous Task Decomposition & Execution Engine

A multi-agent pipeline that ingests a project brief and autonomously plans, researches, drafts and reviews deliverables through role-specialized agents with inter-agent feedback loops. Built with CrewAI and the Anthropic API, with quality-threshold exit conditions and structured output to a finished document.

CrewAIAnthropic APIMulti-agent
View project →
03

Trackr — Agentic Health Tracking & Nutritional Intelligence

An AI agent built on LangChain and the Anthropic API that lets users log workouts and meals in natural language, with tool-calling integrations for real-time nutritional lookup and progress analytics. Persistent memory layer for longitudinal tracking and personalized recommendations.

LangChainAnthropic APITool-calling
View project →
01

Cycle World Pondicherry — Headless Cycle Storefront

Built on Next.js with server-side rendering for SEO-optimized catalogue pages and dynamic product routing. Backed by a normalized Supabase Postgres schema with RLS-enforced access control and Realtime inventory sync, deployed through a Vercel pipeline with edge caching achieving sub-second TTFB.

Next.jsSupabasePostgres RLSVercel Edge
View project →
02

QLess — Multi-Tenant Real-Time Pre-Order & Queue Management Platform

A production-deployed SaaS platform where any food vendor can onboard, publish menus and manage orders through a dedicated staff dashboard. Built on Next.js and Supabase with Realtime-powered live token broadcasting, QR-based customer access, and Postgres RLS-enforced per-tenant data isolation.

Next.jsSupabase RealtimeMulti-tenantQR access
View project →
01

Frabe — Women's Personal Safety App UX/UI Case Study

End-to-end Android safety application, driven by primary research across 80 survey respondents and 12 in-depth interviews. Solved the core usability challenge of reaching emergency help in under 8 seconds through a one-tap SOS flow, horizontally scrollable helpline cards, and a safe-area map surfacing 9+ location categories. High-fidelity screens delivered in Figma, with the interaction model stress-tested through Maze usability testing.

User researchFigmaUsability testing
View case study →
02

QLess — Campus Pre-Order & Queue Management App UX/UI Case Study

Mobile pre-ordering and live token tracking experience for high-footfall campus dining venues, removing physical queues through a streamlined order-to-token flow. Research across canteen visitors, full journey mapping from browse to collection, and 10 high-fidelity screens — onboarding, menu discovery, cart, live order status, order history, profile — built around a sub-3-tap ordering principle.

User researchJourney mappingFigma
View case study →

03 — Known Technologies

What I build with

The stack I reach for across AI systems, production web platforms, and interface design.

Languages

C++C++
CC
PythonPython
JavaJava

Frontend

HTML5HTML5
CSS3CSS3
JavaScriptJavaScript
Tailwind CSSTailwind
Next.jsNext.js
ReactReact

Backend & APIs

Node.jsNode.js
FastAPIFastAPI
FlaskFlask

Databases

PostgreSQLSQL
MongoDBMongoDB
MySQLMySQL
SQLiteSQLite
SupabaseSupabase
FirebaseFirebase

AI & ML

LangChainLangChain
OpenAIOpenAI
AnthropicAnthropic
Hugging FaceHugging Face

DevOps & Tools

DockerDocker
KubernetesKubernetes
GitGit
GitHubGitHub
VercelVercel
FigmaFigma

04 — Experience

Where I've worked

  1. Jan 2026 — May 2026

    Freelance Web Developer

    Built a full-scale webpage end-to-end and handled its SEO.

  2. Jan 2025 — Dec 2026

    Technical Lead — College Department Club

    Led the technical team across club projects: code quality, system design, and mentoring junior developers in frontend and best practices.

  3. Jan 2025 — Dec 2026

    Design Lead — College Department Club

    Led the design team's UI/UX initiatives, mentored junior designers in design thinking and prototyping, and ran workshops on user-centered problem solving.

05 — Education

Where I've studied

  1. 2022 — 2026

    Bachelor of Technology

    Sri Manakula Vinayagar Engineering College

  2. 2021 — 2022

    12th Grade

    Petit Seminaire Higher Secondary School

  3. 2019 — 2020

    10th Grade

    Petit Seminaire Higher Secondary School

Skills

Web
HTMLTailwindJavaScriptNext.js
AI / ML
PythonRAGLangChain
Core
JavaSQL

06 — Contact

Let's talk.

Open to AI engineering, full-stack, and product design roles. If my range across these three feels useful to your team, I'd like to hear from you.

Email Email vsshashank08@gmail.com LinkedIn LinkedIn shashank-sekhar GitHub GitHub hank0811 Phone +91 91502 33560