Building
Intelligent
Systems
with
Code
and
Curiosity
AI/ML & Data Engineer with 2.5+ years spanning AI research, HR-tech product development, and enterprise systems. I design and ship LLM-powered applications — RAG pipelines, multi-agent workflows, and production-style backends — and build the data foundations behind them.
Artificial Intelligence Through an Engineering Lens
My work sits at the intersection of machine learning, data systems, and scalable engineering. My graduate studies in Computer Engineering at George Washington University focus on Machine Learning and Intelligent Systems, where I work on building practical ML systems that move from research ideas to deployable software.
I approach machine learning as an engineering discipline and am interested in the full lifecycle of intelligent systems — from data pipelines and experimentation to infrastructure, deployment, and iteration in production environments.
My work involves designing end-to-end systems that combine classical machine learning, deep learning, and modern AI tooling, including recommendation systems, large language model applications, and cloud-based ML infrastructure. I am particularly interested in the intersection of machine learning systems, generative AI, and scalable data infrastructure.
I enjoy building systems where data, engineering, and machine learning come together to create practical intelligence.
Technical expertise
The core technologies and tools I work with across ML, engineering, and deployment.
Languages
AI / ML
Backend & APIs
Vector Databases
Data & Cloud
Tools
Research & projects
From academic research to hands-on ML projects.
Multi-Agent Research Intelligence System
Building a multi-agent research assistant that analyzes technical papers, compares documents, and produces source-grounded summaries with citation validation and hallucination checking. Orchestrated 7 specialized agents via LangGraph for research-grade Q&A, with a RAG backend exposed through FastAPI.
View DetailsThoracic Disease Detection System
Built a multi-label deep-learning system detecting 9 thoracic diseases from chest X-rays, benchmarking CNN vs. transformer architectures on the NIH dataset (112,000+ images). Trained DenseNet-121 and Vision Transformer models, comparing disease-level AUROC performance. Applied Grad-CAM explainability to localize clinically relevant regions.
View DetailsWork experience
Graduate AI Researcher — HLS RAG Pipeline
Architected the data-engineering layer of a faculty-led RAG pipeline for High-Level Synthesis, processing 500+ heterogeneous C/C++/TCL sources into a clean, retrieval-ready corpus. Built automated task-inventory and cleaning workflows standardizing 8+ metadata fields, cutting manual curation effort by ~60%. Delivered reproducible, documented data assets underpinning retrieval-evaluation experiments and an in-progress paper submission.
Chief Technology Officer & Founding Engineer
Owned end-to-end technical strategy and execution for an early-stage RPO recruiting platform, translating recruiter workflows into product requirements, data models, and automation pipelines from a zero codebase. Designed an AI-powered bulk resume-evaluation engine that parsed resumes/JDs, extracted skill signals, and generated match scores — cutting recruiter shortlisting time ~70% on batches of 1,000+ resumes. Engineered core data architecture across SQL, MongoDB, and Redis-style caching.
Principal Consultant — HCM
Led Workforce Management operations for 11+ multinational clients — including ABFRL, Adani Wilmar, Bestseller, USV, and FCI India — owning attendance, leave, payroll, exit, and employee-lifecycle delivery in production. Developed and debugged 30+ JavaScript/SQL business rules, reports, and automations, serving as primary technical point of contact.
Active research
My ongoing independent research at GWU under Prof. Nan Wu.
HLS RAG Pipeline — Retrieval-Augmented Generation for High-Level Synthesis
Architected the data-engineering layer of a faculty-led RAG pipeline for High-Level Synthesis, processing 500+ heterogeneous C/C++/TCL sources into a clean, retrieval-ready corpus for LLM-grounded analysis. Built automated task-inventory and cleaning workflows standardizing 8+ metadata fields, cutting manual curation effort by ~60%. Delivered reproducible, documented data assets underpinning retrieval-evaluation experiments and an in-progress paper submission.
Academic background
Master of Science, Computer Engineering
Specializing in Machine Learning & Intelligent Systems, with a deep focus on LLMs, retrieval-augmented generation, and design automation — skills that now drive my independent research under Prof. Nan Wu.
Coursework: Pattern Recognition & ML, Advanced ML, Machine Intelligence, Reinforcement Learning, Stochastic Processes, Parallel Computer Architecture, Intro to HPC, Big Data & Cloud Computing, Network Security
Bachelor of Technology, Automobile Engineering
Built a strong engineering foundation in systems thinking, control systems, and applied mathematics — skills that now underpin a deliberate pivot into machine learning and AI.
Let's connect &
build together
I'm actively seeking AI/ML research and engineering roles. Whether you're looking for someone who bridges business strategy with deep technical expertise, let's talk.