Academics

Education, research, certifications, and recognition

Research Interests

LLM Systems Retrieval-Augmented Generation Agentic Workflows Explainable AI AI Security Multimodal AI Natural Language Processing Semantic Retrieval Memory-Augmented Agents Tool-Using AI Systems AI Systems Evaluation

Birla Institute of Technology and Science (BITS), Pilani

WILP (Work Integrated Learning Programme)

M.Tech in Data Science and Engineering

CGPA: 8.14/10 Apr 2022 – May 2024

Relevant Coursework

Machine Learning Deep Learning Natural Language Processing Data Mining Data Structures and Algorithms

Dissertation

Explainable AI for Predicting Malware Infection

Nov 2023 – Apr 2024

Developed an interpretable ML pipeline on the Microsoft Malware dataset (8.9M devices) with GDPR-compatible explainability for cybersecurity applications.

  • Trained ML model achieving ~66.7% accuracy and ~66.4% recall, aiding proactive mitigation of data breaches and financial risks.
  • Applied EBM, SHAP, LIME for interpretability, producing local + global explanations with uncertainty for regulatory + trust alignment (GDPR-compatible design).
  • Engineered features from 4.1GB (83-field) dataset, optimizing memory usage by ~50% via columnar transformations in Pandas/Polars.
EBM SHAP LIME Polars Pandas scikit-learn XGBoost

SRM University, Haryana

B.Tech in Computer Science and Engineering

CGPA: 8.14/10 Jul 2014 – May 2018

Relevant Coursework

Database Management Systems Software Engineering AI and Expert Systems Data Mining Data Structures and Algorithms

Academic Projects

FinSight: Enterprise Multi-Agent Investment Intelligence Platform

Independent Personal Project · May 2026 – Present

Architected a multi-agent AI platform for investment research, orchestrating specialized agents for retrieval, quantitative analysis, market intelligence, analytics, and response validation.

  • Designed a framework-agnostic agent architecture using Google ADK, LangGraph, LangChain, LlamaIndex, CrewAI, PydanticAI, OpenAI Agents SDK, and the Agent-to-Agent (A2A) Protocol.
  • Implemented a unified Model Context Protocol (MCP) server exposing structured financial data, SEC filings, and external knowledge sources.
  • Built hybrid RAG with dense retrieval, BM25 search, reranking, metadata filtering, and persistent conversational memory.
  • Designed evaluation and observability pipelines using RAGAS and Langfuse to analyze retrieval quality, reasoning performance, hallucinations, and end-to-end system behavior.
  • Developed the platform using AI coding tools including Claude Code, OpenCode, and Mimo Code.
Google ADK LangGraph LangChain LlamaIndex CrewAI MCP A2A Protocol RAGAS Langfuse Claude Code OpenCode Mimo Code

Certifications

Azure AI Engineer Associate

Microsoft · June 2025

Acknowledged Contributor — The Hundred-Page Language Models Book

Andriy Burkov · 2025

Awards & Recognition

Best Team Award (2x), On-the-Spot Award (5x), Special Initiative Award

Tata Consultancy Services · 2021 – 2023

Semi-Finalist — TechGig Code Gladiators

TechGig · 2018