Yash KhadseAI ENGINEER
Résumé
YASH KHADSE / HYDERABAD, INDIAAI ENGINEER / FULL-STACK BUILDER

AI ENGINEER.FROM MODELTO PRODUCT.

LLM SYSTEMS/RAG/AGENTS/FULL STACK

THE THINKING BEHIND THE BUILD
CONTENTPROCESSKNOWLEDGE

Extract. Saved content becomes structured text.

SOCIAL BRAIN · CONCEPTUAL PIPELINE

I’m Yash. I build AI systems that connect models to the work they need to do — from grounded knowledge assistants to agents that act.

Explore my work View résumé
SCROLL TO EXPLORE ↓ENGINEERING THE WHOLE SYSTEM
SELECTED WORKFOUR SYSTEMS / FOUR DIFFERENT CHALLENGES

Built beyond
the prototype.

From personal knowledge to enterprise workflows. A closer look at the systems, the decisions, and what came out of them.

01 / FEATURED PROJECT LIVE PRODUCT

Social Brain

A place for everything you save. A cross-platform knowledge base with an AI assistant grounded in your own sources.

NEXT.JS / REACT NATIVE / PGVECTORExplore the build
ARTICLENOTEBOOKMARKKNOWLEDGE INDEXpgvector / hybrid searchGROUNDED ANSWER[1] [2] [3] sourcesEXTRACT → ANALYZE → EMBEDARCHITECTURE ILLUSTRATION
10,000+DOCUMENTSRERANK01020392%ANSWER RELEVANCEevaluated with RAGASHYBRID RETRIEVAL / CROSS-ENCODER RERANKINGARCHITECTURE ILLUSTRATION
02 / Retrieval · Evaluation

Enterprise RAG

Answers grounded in 10,000+ documents. A retrieval system built around relevance, traceability, and continuous evaluation.

92%Answer relevance · RAGAS
VIEW PROJECT
STATEFULMEMORYAGENT 01tool handoffAGENT 02tool handoffAGENT 03tool handoffHUMAN APPROVALLANGGRAPH + CREWAI / ORCHESTRATED DOCUMENT PROCESSINGARCHITECTURE ILLUSTRATION
03 / Agent orchestration · Automation

Agent Workflows

Coordinated agents for document-heavy workflows, with human approval gates and a clear view of system behavior.

70%Less processing time
VIEW PROJECT
A CONVERSATION, WITH CONTEXT.WHISPERspeech to textGPT-4o + MEMORYpersistent vector storeELEVENLABStext to speechCALENDAR / CRM / SEARCH<1.5sLATENCYARCHITECTURE ILLUSTRATION
04 / Voice AI · Realtime systems

Voice & Memory

A realtime voice assistant with persistent memory and tools for calendar, CRM, and search.

<1.5sLatency via async streaming
VIEW PROJECT
FREELANCE SERVICESWEB / APP / AI

What I can
build for you.

Web development

Fast, accessible web apps and marketing sites built with Next.js and React.

App development

Cross-platform mobile apps that share logic with the web, built with React Native and Expo.

AI automations

Automated workflows that connect LLMs to the tools and data you already use.

AI agents & engineering

RAG pipelines, agent orchestration, and voice assistants grounded in your own data.

DISCUSS A PROJECT
THE PERSON BEHIND THE SYSTEMSABOUT ME

An engineer.
Across the
whole stack.

I care about the distance between a model that works and a product people can use.

My work spans AI engineering, full-stack development, and cloud delivery. I completed a Programmer Analyst Trainee period at Cognizant, building and supporting AI/ML solutions for enterprise clients.

Before that, I built voice assistants at NyraAI, delivered AI-augmented applications, and led a six-member development team. The common thread: connect the model, data, and interface into a coherent system.

The full story, in one page
EDUCATION / 2022–2026

B.Tech, Computer Science & Engineering

Data Science · Malla Reddy Engineering College
Hyderabad · Nov 2022–Jul 2026

EXPERIENCE2023 — PRESENT

Learning by
shipping.

Enterprise delivery, early-stage products, and team leadership. Each role added another part of the system.

Mar 2026–Jun 2026

Cognizant

Programmer Analyst Trainee

Built and supported enterprise AI/ML pipelines and FastAPI inference services. Contributed to LLM and RAG accelerators, retrieval tuning, SQL optimization, and delivery quality.

Dec 2025–Feb 2026

NyraAI

AI Engineer

Built a production LLM voice assistant with RAG and agentic workflows, improving context accuracy by 35% and reducing hallucination rate by 40%. Implemented guardrails, monitoring, fallback strategies, and quality regressions.

Sep 2025–Nov 2025

Defence in Depth Solutions

Full Stack Developer

Developed AI-augmented enterprise applications, LLM-powered search, and form parsing. Delivered client-facing POCs, secure APIs, technical designs, and handover documentation.

Jul 2024–Aug 2025

Atharva Data Science Community

Technical Lead

Led delivery of 5+ MERN applications with AI/ML integrations and mentored a six-member development team. Improved MongoDB query and schema efficiency by 30% through data-model optimization.

Nov 2023–Feb 2024

Brutanix

Web Developer Intern

Reduced API latency by 15% and built 20+ reusable React/TypeScript components that improved frontend performance by 40%. Implemented JWT/OAuth authentication and secure API design.

CAPABILITIESMODEL → PRODUCT → PRODUCTION

The working toolkit.

AI systems

Retrieval, agents, and voice interfaces with evaluation built into delivery.

  • RAG pipelines
  • LangChain
  • LangGraph
  • CrewAI
  • RAGAS / DeepEval
  • Tool calling

Product engineering

The APIs and interfaces that turn a working model into a usable product.

  • Python
  • TypeScript
  • FastAPI
  • React
  • Next.js
  • React Native

Data & delivery

Searchable data, asynchronous jobs, and dependable deployment workflows.

  • PostgreSQL
  • Vector databases
  • Redis / BullMQ
  • Docker
  • AWS / GCP
  • CI/CD
LET’S CONNECTYOUR NEXT AI ENGINEER

Good problems.
Thoughtful builds.
Let’s talk.

Have an AI engineering role or a challenging technical problem in mind? I’d like to hear about it.

Say hello