Architecting Systems That Think, Retrieve & Act
A deep dive into my professional track record, educational background, verified industry certifications, soft skills, and engineering philosophy.
Mission & Philosophy
I believe the real potential of artificial intelligence is unlocked not by raw parameter counts alone, but through deterministic orchestration, groundable retrieval, and autonomous multi-agent division of labor.
Whether engineering an enterprise RAG pipeline that eliminates hallucination via strict page-level source tracing, or benchmarking YOLO detection heads for medical classification, I emphasize empirical verification, low latency, and rapid delivery from prototype to production.
Core Competencies
- Agentic AI & Model Context Protocol (MCP)
- Enterprise Hybrid Vector Retrieval (Dense + BM25)
- Computer Vision Benchmarking (YOLOv8/v11/v26)
- High-throughput FastAPI / PostgreSQL pgvector backends
- Explainable AI (SHAP) & Tabular Classification (XGBoost)
- Business Intelligence & Dashboarding (Tableau & Power BI)
Hands-On Technical Leadership
AI Engineer & Data Analyst
Applied Research & Independent Engineering · 2024 - Present- Built an enterprise-grade, production-oriented RAG platform enforcing JWT authentication & RBAC filtering, query rewriting, an Agent Planner routing across Document RAG & GraphRAG (bounded to 3 steps), RRF fusion, cross-encoder reranking, and grounded answers with Nemotron via FastAPI and PostgreSQL + pgvector.
- Engineered an end-to-end Hybrid RAG pipeline combining dense vector embeddings (HuggingFace all-MiniLM-L6-v2) and BM25 sparse retrieval into a Pinecone hybrid index, ensuring strict page-level source traceability with Google Gemini 2.5 Flash.
- Orchestrated autonomous multi-agent systems (LangChain, Tavily API, BeautifulSoup, Gemini 2.5 Flash) featuring Research, Reader, Writer, and self-auditing Critic agents with Streamlit web UI (live logs) and CLI execution modes.
- Conducted deep learning computer vision research on mammography classification benchmarking YOLOv11 & YOLOv26 on CBIS-DDSM & VinDr-Mammo; trained custom YOLOv8 object detection to 92% accuracy with ONNX export.
- Developed end-to-end data analysis workflows in Python/Pandas, Scikit-learn, XGBoost (with SHAP explainability), and created business intelligence reporting using Tableau, Power BI, and Microsoft Excel.
Education & Credentials
Degrees
Master of Computer Applications (MCA)
Galgotias University
Bachelor of Computer Applications (BCA)
Chandigarh University
Senior Secondary (10+2)
T.P.S College
Matriculation (10th)
Dr. D. Ram DAV Public School
Verified Certifications
Oracle Agentic AI Foundations
MITS: Faculty Development Program on Agentic AI
Oracle Cloud Infrastructure AI Foundations
Oracle Cloud Infrastructure Certification
Microsoft Excel 2026: Pro Mastery
Data Analysis, Formulas, Pivots & Reporting
Data Science Mastery 2025: Excel, Python & Tableau
Comprehensive data exploration, pipelines & BI
Professional Attributes & Soft Skills
Leadership
Guiding technical roadmaps, prioritizing sprint backlogs, and cross-functional direction.
Teamwork
Seamless collaboration with researchers, product managers, and backend engineers.
Communication
Articulating complex vector architectures, model trade-offs, and metrics clearly.
Planning & Strategy
Structured milestones, backlog prioritization, and iterative execution.
Time Management
Agile sprint cadence, rapid MVP turnaround in days, and meeting deadlines reliably.