Seasoned Data Engineering Leader with over 12 years of experience architecting and delivering
enterprise-scale data solutions aligned with organizational objectives across diverse industries.
Proven Team Leadership, currently spearheading a high-performing data engineering team, driving
end-to-end project execution, skill development, and operational excellence.
Expert in Scalable Data Architecture, specializing in building, optimizing, and automating robust
data pipelines focused on ingestion, orchestration, transformation, and quality control.
Achieved 75% Reduction in Processing Time through the strategic design and deployment of highefficiency
ETL workflows, significantly enhancing system performance and throughput.
AI-Orchestrated DevOps Pipeline — End-to-end automation using Claude Code from Jira ticket
ingestion → Terraform IaC generaon → GitHub PR workflow → Cloud Build CI/CD → BigQuery
provisioning → Airflow DAG-based ETL orchestration.
Semantic Product Search Engine — Built using Gemma 3 embeddings with HNSW, IVF, and PQ
indexing strategies on a Vector Database for high-performance similarity search at scale.
Cloud Transformation Specialist, leveraging AWS and GCP to lead successful cloud migrations that
improved scalability, performance, and data availability.
Operational Scale Champion, led the implementation of a data platform capable of processing over
4,000 files daily while maintaining 99.9% accuracy and meeting strict SLA standards.
Hybrid RAG System, Implemented Dense Vector Retrieval, Sparse Keyword Retrieval, Reciprocal
Rank Fusion (RRF), Response Generation.
MLOps, ML Model Development & Experiment Tracking, Data & Code Versioning, Model Building,
Experiment Tracking.
Subjects
-
Data engineer Beginner-Expert
-
AI agents Beginner-Intermediate
-
Agentic AI Beginner-Intermediate
Experience
No experience mentioned.