Skip to main content
ONLINE_V2.0

KiranSheoran

Bachelor of Engineering in Information Technology Student

Portrait of Kiran Sheoran

Information Technology engineering student with experience building AI/ML, agentic AI, Android, and data-driven applications. Winner of Smart India Hackathon 2025 and finalist at Barclays Hack-O-Hire 2026.

Experience

Professional trajectory

Joint Secretary

Competitive Programming Club
Oct 2024 — Present

Organized a 700+ participant national-level hackathon, conducted DSA workshops for 200+ students, and mentored students in DSA and problem-solving strategies.

Organized a 700+ participant national-level hackathon
Conducted DSA workshops for 200+ students
Mentored students in DSA and problem-solving strategies

Projects

Selected works & experiments

A

AML SAR Investigator Agent - Barclays Hack-o-Hire

Built an autonomous AML investigation system using LangChain AgentExecutor with tool-calling across 5 datasets (3,000 customers, 56,000+ transaction records) to investigate fraud alerts step-by-step. Engineered 6 LangChain @tool functions covering KYC profiling, account analysis, suspicious transaction extraction, and SAR deduplication logic to reduce false positives. Designed a 7-section sequential SAR generation pipeline grounded in an evidence JSON schema, preventing LLM hallucination by restricting each section to verified tool outputs only. Integrated Langfuse observability (self-hosted via Docker) for full agent trace capture and built a 3-panel Streamlit UI for live trace inspection and analyst review of SAR drafts before filing.

LangChainGroqLangfuseStreamlit
F

Fish Catch Identification - SIH 2025 Winner

2025

Won 1st place nationally at Smart India Hackathon 2025 (ISRO) — built an offline-first Android app classifying 12 fish species using YOLOv8 + TensorFlow Lite, deployed for fishermen in low-connectivity coastal regions. Achieved 97% accuracy in species detection and freshness analysis entirely on-device without internet connectivity. Implemented coin/ArUco marker-based volume estimation using OpenCV with biological weight-length formulas and dual-model inference pipeline balancing real-time preview speed with capture accuracy. Designed offline-first SQLite + Firebase Firestore sync using Android WorkManager for automatic background upload of geo-tagged catch data.

AndroidKotlinTensorFlow LiteOpenCV

Stack

Tools & Technologies

JavaC++PythonJavaScriptCReactJSNodeJSExpressJSREST APIsLangChainFastAPIStreamlitGitGitHubVS CodeDockerSQLMongoDBRelational DatabasesAgentic AILangfusePrompt EngineeringRAGVector DBFine TuningBasic MLOpsData Structures & AlgorithmsObject-Oriented Programming (OOP)DBMSGoogle Cloud Platform (GCP)KubernetesCI/CD

Education

Academic background

2028

Army Institute of Technology

Bachelor of Engineering - Information Technology

GPA: 8.7

Smart India Hackathon 2025 Winner Certificate

ISRO

Dec 2025

Barclays Hack-O-Hire Finalist Certificate

Barclays

Mar 2026

Deutsche Bank Scholar Selection

Deutsche Bank

Feb 2025

Kiran Girls Scholarship Selection

Persistent Foundation

Jan 2025

Partex AI AlgoFusion Hackathon Finalist

Army Institute of Technology

Apr 2026

6-Star Mark on HackerRank's Problem Solving Category

HackerRank

Dec 2024

More Portfolios

Built withclickfolio.me