Ramya Baliga-Bhatt

Data Engineer | AI & Agentic Systems Specialist

San Francisco, CA

Open to Work US Green Card ยท No Sponsorship Required โ†“ Download Resume
0
Years Experience
0
Databases Managed
0
GB/day Data Processed
0
M+ Records Queryable

About Me

Data Engineer with 7+ years building production-grade ETL/ELT pipelines and cloud data warehouses at enterprise scale. Specializes in AI-driven and agentic data systems โ€” autonomous error detection, LLM-powered natural-language data interfaces, and full-stack delivery from ingestion to production-ready dashboards. Currently pushing the frontier of self-healing data infrastructure and agentic coding workflows.

Work Experience

Data Engineer
Johnson & Johnson
Jun 2022 โ€“ Dec 2024 | Limerick, Ireland
  • Built 15+ production ETL pipelines processing 500GB/day
  • Reduced pipeline runtime by 40%, eliminated 10 recurring failure points
  • Designed data models supporting 50+ downstream reports
  • Led solo Azure subscription migration with zero downtime
Data Analytics Developer
Johnson & Johnson
Jun 2021 โ€“ Jun 2022
  • Built 20+ Tableau/Power BI dashboards for 50+ stakeholders
  • Conducted EDA on 15+ datasets, 60% recommendations adopted
Business Data Analyst
Johnson & Johnson
Jan 2021 โ€“ Jun 2021
  • Managed 8+ data projects, 100% deadline compliance
  • Built 50+ dashboards
Software Developer
Johnson & Johnson
Sep 2019 โ€“ Jan 2021
  • Built iOS app serving 5,000+ daily visitors
Junior Software Developer
Awnics
Mar 2016 โ€“ Jul 2017

Skills & Expertise

Autonomous Agent Systems

Multi-Agent Orchestration Autonomous Error Detection Self-Healing Pipelines Agent Decision Systems Failure Recovery Tool Use & Function Calling

Production LLM Engineering

Retrieval-Augmented Generation LLM Evaluation Frameworks Multi-Model Routing Prompt Engineering Text-to-SQL Context Window Management

AI Reliability & Observability

Production AI Monitoring Pipeline Health Dashboards Automated Quality Gates Data Lineage Tracking Hallucination Mitigation Latency Optimization

AI Infrastructure

Vector Databases Containerized AI Deployment API Design for LLM Systems Cloud Data Platforms DAG Orchestration

Data Engineering Core

ETL/ELT Pipeline Design Cloud Data Warehouses Data Modeling SQL Optimization PySpark Python

DevOps & Delivery

Docker & Container Registry CI/CD Pipelines Git Version Control Agile/Scrum Infrastructure as Code Zero-Downtime Deployments

Featured Projects

AskMyData

LLM-powered text-to-SQL app for querying World Bank datasets in natural language with multi-provider failover (Claude, GPT-4o). Parquet + DuckDB pipeline for sub-second queries on 100M+ records.

Python LLM DuckDB Streamlit
View Project โ†’

Self-Healing Data Pipeline

Autonomous ETL error-recovery framework with regex rules engine (80%+ auto-fix) and LLM fallback. Self-learning knowledge base, 8 remediation strategies, Dagster integration.

Python Dagster LLM SQLite
View Project โ†’

Developer Portfolio Website

Responsive portfolio in Next.js 16, React 19, Tailwind CSS 4 with dark/light theming and animations.

Next.js React Tailwind CSS
View Project โ†’

Certifications

Industry Certifications
Microsoft Certified: Azure Fundamentals Microsoft Certified: Azure Data Fundamentals Scrum Alliance Certified ScrumMaster (CSM)
LinkedIn Learning Certificates
Generative AI for Business Leaders Introduction to Prompt Engineering for Generative AI Prompt Engineering: How to Talk to the AIs Cloud Concepts: Determining Your Cloud Strategy Advanced SQL for Query Tuning and Performance Optimization DevOps Foundations Learning Power BI Desktop Cloud Architecture: Core Concepts Cloud DevOps Concepts: Understanding Processes and Services Analyzing Big Data with Hive

Get in Touch