KP
Open to Internships, Research & Full-Time · ASU '27

KRISH
PATEL

Building intelligent systems at the intersection of AI engineering and full-stack development. M.S. Computer Science @ Arizona State University — specializing in LLMs, RAG pipelines, and scalable architectures.

4+
Roles
10+
Projects
4.0
GPA
Scroll

About Me

Who I Am

KP

AI Engineer &
Full-Stack Builder

I'm Krish Patel, a graduate student at Arizona State University pursuing an M.S. in Computer Science (GPA: 4.0/4.0), graduating May 2027. I hold a B.Tech. in ICT from Pandit Deendayal Energy University (CGPA: 9.24/10, May 2025).

I build production-grade AI systems — fine-tuning large language models, constructing RAG pipelines, designing knowledge graphs, and deploying agentic workflows. On the engineering side, I architect full-stack platforms with React, Flask, Node.js, and cloud infrastructure.

My work bridges cutting-edge AI research with real-world impact. As a Graduate Research Assistant at ASU, I build Legal AI multi-agent systems. I've improved model accuracy by 25%, reduced API latency by 20%, and deployed systems at scale on AWS using Docker and CI/CD pipelines.

25%
Accuracy gain
35%
Speed boost
92%
Match precision
Current Role
Graduate Research Assistant
Arizona State University · Prof. Hasan Davulcu · Tempe, AZ
AI Specialization
LLM Engineering & Generative AI
RAG · Fine-tuning · Agents · Knowledge Graphs
Engineering Stack
Full-Stack Development
React · Flask · Node.js · PostgreSQL · Docker
Cloud & DevOps
AWS · GCP · Docker · CI/CD
Nginx · Linux · REST APIs
Location & Availability
Tempe, Arizona, USA
Open to remote, hybrid & relocation

Technical Expertise

Skills & Technologies

A dual-threat engineer with deep expertise in AI/ML systems and modern full-stack development.

🤖
AI / ML Engineering
LLMs · Deep Learning · Data Science
Languages
PythonC++JavaKotlinSQLShell
Frameworks
PyTorchTensorFlowScikit-LearnLangChainLangGraphTransformersHugging FaceOpenAI APIPandasNumPy
Tools & Cloud
DockerAWS BedrockAWS LambdaGCPFastAPIFlaskStreamlitNeo4jJenkinsGit
Specializations
Generative AILLM Fine-TuningRAG PipelinesAgentic WorkflowsLegal AIKnowledge GraphsMulti-Agent Systems
Full-Stack Development
Frontend · Backend · DevOps
Languages
JavaScriptTypeScriptPythonJavaKotlinSQLC++
Frameworks
ReactNext.jsNode.jsExpressFlaskDjangoSpring BootJetpack ComposeFastAPI
Databases
PostgreSQLMySQLMongoDBNeo4jDynamoDBRedisFirebase
DevOps & Cloud
DockerAWS (EC2/Lambda/S3)GCPJenkinsCI/CDNginxLinuxNDK/JNI

Work History

Experience

Building production AI and full-stack systems at fast-growing tech companies.

Graduate Research Assistant
2025 – Present
Arizona State University · Prof. Hasan Davulcu · Tempe, AZ
  • Architected scalable Legal AI multi-agent systems for automated case analysis and reasoning
  • Built modular LangGraph agent pipelines coordinating retrieval, drafting, and review stages
  • Benchmarked LLM agents on large legal corpora, improving response answer accuracy by 25%
  • Optimized inference workflows on multi-GPU clusters, cutting end-to-end processing time by 35%
LangGraph Legal AI Multi-Agent LLMs HPC Clusters
Data and Reporting Assistant
2025 – Present
W. P. Carey School of Business, ASU · Tempe, AZ
  • Automated Salesforce opportunity field updates with Python and Selenium, saving 6+ hours weekly
  • Built automated multi-year Excel workbook matching Lavidge ad data to 3,000+ Salesforce records
  • Delivered GA4 web analytics and monthly campaign performance summaries for executives
  • Streamlined automated reporting pipelines, reducing manual data entry errors by over 30%
Python Selenium Salesforce GA4 Excel Automation
Data Science & LLM Intern
Dec 2024 – May 2025
Blink Analytics · India
  • Built interactive analytics dashboards and modular Flask REST APIs serving 10K+ daily queries
  • Designed optimized relational schemas and Redis caching, cutting query response time by 28%
  • Engineered RAG retrieval pipelines with LLM endpoints for document search across 5K+ records
  • Shipped containerized AWS deployments with Docker and Nginx, boosting service uptime to 99.5%
LLMs RAG React Flask Redis AWS Docker
AI / ML Intern
May 2024 – Jul 2024
Neurapses Technologies · India
  • Developed modular Flask REST APIs linked to Neo4j graph DB for intelligent data retrieval
  • Integrated multiple AI model endpoints and managed schema versioning via Alembic migrations
  • Reduced API latency by 20% through query indexing, connection pooling, and result caching
  • Built automated test suites raising endpoint code coverage to 85% and cutting regressions
Neo4j Knowledge Graphs Flask LLMs Alembic Python

Portfolio

Projects

From AI agents to full-stack platforms — engineering solutions that push the boundary of what's possible.

InsureBot: AI Insurance Coverage Assistant

Multi-agent chatbot that searches insurance policies online in real-time and tells you whether a medicine is covered by your plan — or recommends alternatives that are covered, and which plan to switch to if needed. Every answer comes with cited evidence from live web searches. Built with LangGraph multi-agent orchestration, Tavily for web search, AWS Bedrock as the LLM backend, deployed serverlessly on AWS Lambda. Voice-enabled via ElevenLabs — ask by voice, get a spoken reply.

LangGraph Multi-Agent Tavily AWS Bedrock AWS Lambda ElevenLabs Python
▶ Demo
02
LLM ResearchHPC

Qwen3 Benchmarking on TAU Bench (HPC)

Benchmarked Qwen3 8B/14B/32B variants on Tau Bench across HPC clusters, tracking response quality, latency, and cost. Analyzed error patterns and built evaluation dashboards to surface failure modes. Improved responses via RLMs, prompt strategies, and multi-agent architectures.

Qwen3TAU BenchHPC ClustersRLMsMulti-Agent
03
Full-StackAI/MLAWS

NextStep: AI Career Recommendation Platform

Full-stack career platform with React, Flask, and Neo4j for path recommendations. Implemented secure JWT authentication and modular APIs delivering real-time skill insights. Modeled skill relationship graphs in Neo4j enabling sub-second traversal across 10K+ nodes. Deployed via Docker and AWS EC2, achieving 92% skill-match accuracy across 1K+ resumes.

ReactFlaskNeo4jJWTDockerAWS EC2
View on GitHub →
04
Full-StackCloud

DataSphere: Cloud Data Visualization System

Full-stack data analytics tool with a dynamic SQL query engine and caching layer for real-time data visualization. Optimized PostgreSQL schema and implemented Redis caching, reducing load times by 35%. Built with Node.js, React, and PostgreSQL, deployed via Docker.

Node.jsReactPostgreSQLRedisDocker
05
AI AgentLLMRPA

ClickLess AI: Human-in-the-Loop Conversational Web Automation

Human-in-the-loop conversational web automation with LangGraph, Playwright, and FastAPI. Designed a LangGraph state machine with intent detection and hard purchase confirmation gate. Implemented MongoDB preference store with adaptive scoring. Added Redis caching layers, cutting query latency 40% over 1K+ requests.

LangGraphPlaywrightFastAPIMongoDBRedisPython
View on GitHub →
06
ResearchLLMHPC

CREST: Medical Agent Benchmarking

Benchmarked multiple LLM agents on MedAgentBench, CraftMD, and AgentClinic clinical tasks. Ran distributed benchmark jobs on ASU Sol supercomputer with SLURM, Apptainer, and Gaudi2. Evaluated diagnostic accuracy across 1K+ clinical cases, surfacing key agent failure modes. Presented a CREST Phase 2 research poster on multi-agent medical reasoning results.

LLM BenchmarkingSLURMApptainerGaudi2ASU Sol HPC
View on GitHub →
07
Hackathon WinnerMulti-AgentEdTech

Mistake Museum: Multi-Agent Math Tutor

Seven-agent LangGraph math tutor diagnosing and correcting common student errors. Distinct agent roles for hinting, grading, and feedback using Kiro IDE and AWS. Error-classification engine across 200+ problem types with 90% accuracy. Won the education track at a hackathon with a full spec-driven dev workflow.

LangGraphAWSKiro IDEMulti-AgentPython
View on GitHub →
09
AndroidKotlinEmbedded

DriveDeck: In-Vehicle Android Infotainment App

Native in-vehicle Android app in Kotlin and Jetpack Compose for infotainment controls. Integrated native C++ modules via NDK/JNI bridges for low-latency hardware signal processing. Configured Jenkins CI/CD pipelines automating builds and tests across 3 device targets. Optimized UI render performance, achieving smooth 60 fps on constrained embedded hardware.

KotlinJetpack ComposeNDK/JNIC++Jenkins
View on GitHub →
10
AI AgentAutoMLResearch

AutoResearch: Autonomous Multi-Agent ML Pipeline

Autonomous multi-agent pipeline for end-to-end ML experimentation and model tuning. Automated hyperparameter search and model selection, cutting research iteration time by 50%. Designed agent orchestration logic for data prep, training, and evaluation handoffs. Pitched to a robotics industry contact, validating real-world research use cases.

Multi-AgentAutoMLLangGraphPythonHPC
View on GitHub →

Academic Journey

Education

4.0/4.0
GPA
M.S. Computer Science
Arizona State University
📍 Tempe, Arizona 🎓 May 2027
Artificial IntelligenceCloud ComputingAgentic AIData Processing at ScaleSoftware EngineeringDatabase Management SystemsSVVT
9.24/10
CGPA
B.Tech. Information & Communication Technology
Pandit Deendayal Energy University
📍 Gujarat, India 🎓 May 2025
Machine LearningDeep LearningData MiningWeb TechnologiesData StructuresOperating Systems

Achievements

Recognition & Contributions

🥇
Hackathon Winner — Mistake Museum

Won the education track at a hackathon for Mistake Museum, a seven-agent LangGraph math tutor with a spec-driven dev workflow and 90% error classification accuracy.

🏆
Top 5 — Innovation Hacks 2.0

Placed top 5 at Innovation Hacks 2.0 for PrismRx, an AWS Bedrock RAG clinical copilot that cut hallucination by 30% and scaled to 500+ concurrent users serverlessly.

💻
Event Management Head — Encode Club

Led as Event Management Head of Encode coding club at PDEU for 12 months, organizing and executing 10+ technical events for the student developer community.

Hackathon Recognition — SIP & Odoo Combat

Recognized for scalable backend and database architecture across SIP and Odoo Combat hackathons, demonstrating expertise in high-performance system design under time constraints.

Get In Touch

🚀

Let's Build Something Incredible

Whether you're looking for an AI engineer, a full-stack developer, or a passionate problem-solver — I'd love to connect. Currently seeking internships, research collaborations, and full-time opportunities.