Data Engineering | MLOps | Backend Infrastructure
Learning to Craft systems that survive scale.

I am an Associate Data Scientist and engineer focused on the intersection of machine learning, distributed systems, and backend infrastructure. I view MLOps not just as a set of tools, but as a commitment to system correctness, reproducibility, and engineering rigor. My goal is to bridge the gap between abstract data science and real-world software engineering, ensuring that models perform under practical constraints like scale, latency, and hardware failure.

Core Engineering Focus:

• MLOps & Lifecycle Engineering: Architecting reproducible training pipelines, implementing robust experiment tracking, and managing cross-environment compatibility (TensorFlow, PyTorch, R) across GPU-enabled Kubernetes clusters.
• Multi-Agent AI & RAG Architectures: Designing orchestration frameworks for autonomous agent coordination. I build retrieval-augmented generation pipelines that seamlessly connect LLM reasoning with structured, vector-based knowledge systems.
• Backend & Distributed Systems: Developing resilient backend services utilizing FastAPI, Flask, and Node.js. My work includes designing API gateway layers and integrating microservices with secure, traffic-managed communication patterns.

I am actively interested in collaborating on scalable ML infrastructure, data platforms, and agentic systems. If you are building robust production-grade architecture, I am always open to thoughtful conversations.

An end-to-end ingestion and transformation engine.

• Architecture Flow:
  Raw Data → Fast API Ingestion → Transformation (Pandas/Spark) → PostgreSQL → K8s Scaled Endpoints
• Focus: Managing the full lifecycle—from raw ingestion to structured insights—while scaling workloads dynamically using Kubernetes and exploring distributed processing.

Multi-agent system designed to reduce manual SRE overhead (Final Year Project).

• Capabilities: Intelligent system orchestration, live monitoring & observability, and strict compliance automation.
• Impact: Built with a systems-first mindset to autonomously manage infrastructure bottlenecks and automate routine SysAdmin tasks.

A multi-agent AI system built for policy understanding and IRDAI compliance checking.

• Capabilities: QA over complex PDF policies, coverage gap detection, and personalized insurance recommendations.
• Tech Highlight: Deep RAG pipeline utilizing FAISS + Embeddings, with complex LLM orchestration handled via LangChain.
• (Note: This is the system that secured my Data Science Internship!)

• Technical Head & Ambassador, DSA Club: Spearheaded technical initiatives and organized major inter-college events (like the 6-hour DATAWEB hackathon).
• Tech Evangelism: Conducted 5+ deep-dive technical sessions reaching 200–300+ students.
• Curriculum: Taught Data Science fundamentals, API integrations, real-world data workflows, and applied ML concepts with practical, live demos.

Core & Backend:

Data & MLOps:

Infrastructure & Cloud:

Databases: