YR

CSE Β· Software Engineer

Building reliable software and learning fast.

Yasaswi Raj Madari

M.S. CS @ UBuffalo Β· AI Engineer @ TummyTales

Hi, I'm Yasaswi Raj Madari β€” building agentic AI systems and full-stack products that ship.

AI Engineer @ TummyTales, building multi-agent systems and RAG pipelines. 3+ years shipping Angular, React, FastAPI at FactSet + SafetyKnights. M.S. CS (ML/AI Focus), UBuffalo, Jan 2026.

AI Engineer (RAG Β· Multi-Agent Β· LLMs)Full-stack (Angular + React + FastAPI)Test automation (Cypress/Playwright)
Yasaswi Raj Madari

Profile

Software Engineer

AI-ready

Education

M.S. CS & Engineering (ML/AI Focus) @ UBuffalo (Jan 2026). Building agentic AI at TummyTales.

Currently

AI Engineer @ TummyTales. Open to full-time SWE / AI Engineer / Full-stack roles.

3+

years SWE

5/5

Google Foobar

#17

IEEExtreme 14.0

AI Assistant Online

Too lazy to scroll? Let Astra Lite do the talking.

Ask about my FactSet work, test migrations, ML projects, or why I deserve coffee for surviving Protractor. Get instant answers, no scrolling required.

Try asking:β€œQuick introβ€β€œWhat’s your strongest stack?β€β€œTell me about ML work”
Start chatting

Powered by Gemini AI β€’ Free & instant

Skills

What I bring to a team

A blend of computer science rigor and product thinking. I value clarity, observability, and building foundations that scale with the roadmap.

AI / LLM Engineering

Building production agentic systems: multi-agent orchestration, RAG pipelines, guardrails, and LLM evaluation.

RAG SystemsMulti-Agent OrchestrationLangChainLlamaIndexGemini APIPrompt EngineeringpgvectorHuggingFace

Full-Stack Engineering

End-to-end from Angular 19 components to FastAPI services. Frontend polish meets backend reliability.

Angular 19ReactNext.jsTypeScriptFastAPINestJSPostgreSQLSupabase

Testing & DevOps

Migrated test suites, cut test time ~30-40%, reduced flakiness ~20%. Docker, AWS, CI/CD.

PlaywrightCypressDockerAWS (EC2/S3)CI/CDgdbUNIX

Projects

Selected work

I thrive in the intersection of product and platform: building experiences that feel sharp, while making sure the system underneath is easy to maintain and extend.

YashStudio.tech β€” RAG AI Portfolio

Live β†—

Recruiter-facing RAG assistant built with text embeddings, pgvector semantic search, and token-aware context management. Three interaction modes: UI, chat, and voice.

Live at yashstudio.tech β€” fully production-deployed on DigitalOcean + AWS.

RAGFastAPIpgvectorGemini APINext.jsDocker

A.R.M.A (coding.Studio())

In-depth

Automated event-permission and facility-booking workflows for campus management.

Reduced admin workload by ~40% through streamlined approval processes.

ReactNode.jsMongoDBExpressTailwindCSS

Debugging C (IEEE - VBIT SB)

In-depth

Full-stack C programming contest platform with real-time leaderboards. Designed the DB schema, built frontend + backend solo, deployed on PaaS.

99% uptime during peak competition events.

Full-stackDatabase DesignCMongoDBDeployment

Experience

How I work with teams

From internships to research labs, I ship in small increments, keep stakeholders in the loop, and lean on metrics and documentation to de-risk delivery.

AI Engineer

TummyTales

Feb 2026 β€” Present
  • Architected a 5-agent AI microservices system (health advisor, nutritionist, etc.) with Agent-to-Agent communication.
  • Built RAG pipelines using text embeddings and pgvector semantic search. Deployed on AWS with Dockerized microservices.
  • Implemented domain-restricted guardrails and clarification-vs-answer routing.

Software Engineer

SafetyKnights

Jan 2025 β€” Jun 2025
  • Built bidding marketplace connecting EHS safety professionals with clients. Optimized Angular 19 + TailwindCSS component tree, cutting page load ~35%.
  • Designed indexed PostgreSQL schema, improving query time by ~40%.

Software Engineer

FactSet

Jun 2022 β€” Jul 2024
  • Built central dashboards and data pipelines. Refactored 100+ legacy AngularJS 1.x modules to modern Angular (TypeScript).
  • Led test migration Protractor β†’ Cypress β†’ Playwright: reduced test time ~30-40%, cut flakiness ~20%.

AI / LLM Engineering

Shipping agentic AI, not just notebooks

M.S. CS (ML/AI Focus) @ UBuffalo. Now building production multi-agent systems at TummyTales β€” RAG pipelines, A2A communication, domain guardrails, and LLM evaluation at scale.

Multi-Agent Orchestration

Designed and shipped a 5-agent AI microservices system at TummyTales with A2A communication, domain guardrails, and clarification routing.

RAG Pipelines

Built production RAG systems using pgvector, text embeddings, token-aware chunking, and semantic search. LangChain + LlamaIndex in the toolbox.

Production AI mindset

LLM evaluation, monitoring, guardrails, and human-in-the-loop design. Not just notebooks β€” shipped and deployed on AWS + DigitalOcean.

Mindset

Code + cameras + caffeine.

I ship agentic AI and full-stack features. Survived Protractor, learned gdb, built RAG systems. Also: design + video editing side quests. Buffalo winters built character.

Fast iteration. Shipped 5-agent AI system at TummyTales, cut SafetyKnights page load by 35%, reduced FactSet test flakiness by 20%.

Full-stack foundation + production AI. Not just RAG demos β€” actually deployed, monitored, and evaluated.

Google Foobar 5/5, IEEExtreme rank 17/4000. Competitive coding meets production software.

Let's talk

Open to full-time SWE, AI Engineer, and Full-stack roles.

Currently building at TummyTales. Looking for teams that ship fast, care about product, and value AI-enabled systems. I respond quickly β€” let's build something.

πŸ“§ yasaswirajmadari@gmail.com

🌐 yashstudio.tech

πŸ’» github.com/yasaswiraj