IST
Field Report · Portfolio

Abhinav Raj

I build AI products, full-stack systems, and web experiences that make an idea easier to use, explain, and ship.

  • 5Shipped products
  • 27+Verified credentials
  • 3Focus areas
Editorial portrait of Abhinav Raj
Photographed at the desk · Vol. 1, No. 1
About Me

Build clearly
Test quickly
Keep it useful

My work sits between engineering, product thinking, and design. I care about interfaces that explain themselves, systems that hold up under real use, and AI features that stay understandable to the person using them.

I started with privacy tools, file workflows, and edge-native services, then moved deeper into AI infrastructure: gateways, agents, retrieval, and the practical plumbing required to make model-based products reliable.

The goal is not to make the work sound bigger than it is. It is to build useful things, document the decisions clearly, and leave each project with a path to improve.

Now

CLEX AI

Building one endpoint for model access, provider routing, API keys, usage visibility, and playground testing.

Recent

Privacy and utility tools

Shipped work across file movement, disposable mail, receipt parsing, and race-weekend intelligence.

Learning

Machine learning systems

Working through Stanford CS229 material while applying the concepts to practical product infrastructure.

Open to

Focused collaboration

AI builds, product engineering roles, technical prototypes, and projects where design and engineering both matter.

See the work Or send a brief
By Abhinav Raj · Product Engineer

AI Builder

  • LLM workflows, agents, and model gateways
  • Automation for bounded, repeatable project work
  • Human-reviewed outputs with clear fallbacks

Full-Stack Developer

  • Frontend systems with clean product flows
  • APIs, auth, storage, and edge deployment
  • Prototypes structured to grow into products

Intelligent Web Experiences

  • Editorial interfaces with useful motion
  • Privacy-aware tools and thoughtful data handling
  • Project pages that explain the work clearly
Builder
Project Notes
Thoughts in Progress

Agentic tools

I use agents for bounded work such as research triage, document parsing, UI QA, code review, and repeated project operations. The useful pattern is a clear input, a narrow output, and a verification step.

Privacy by design

For file movement, mail, and AI tooling, privacy starts in the architecture. I avoid unnecessary storage, keep permissions explicit, minimize data collection, and make it clear what leaves the device.

Interfaces with restraint

I keep interfaces focused on the action that matters. Motion, typography, and visual effects should guide attention instead of competing with the workflow.

Human first AI

AI should make a product easier to trust and operate. I design AI features with clear fallbacks, editable outputs, visible reasoning where useful, and controls that keep the final decision with the user.

Selected
Work

Slide through 5 projects