Professional Summary

Data Systems and Machine Learning Engineer with experience designing high-throughput batch and real-time data pipelines, lakehouse architectures, and production ML platforms on AWS and Azure. Skilled in Spark, Kafka, Databricks, and vector search systems, with a strong focus on building scalable, reliable data and ML infrastructure for real-world applications.

🌍 India and open for relocation
✉️ csprathyy@gmail.com
🤝 Open to Data Engineer | Data Scientist | ML Engineer roles

• High-throughput batch & real-time data pipelines (Spark, Kafka, Kinesis, Flink)
• Lakehouse architectures using Delta, Iceberg, Hudi, Unity Catalog
• Streaming analytics & security detection systems
• ML pipelines on Spark with GPU acceleration
• Vector search & semantic retrieval systems using FAISS & embeddings
• Multimodal RAG systems (text + image retrieval)
• Production ML with monitoring, CI/CD, and drift detection

PySpark Kafka Kinesis Flink Databricks Delta Lake Iceberg Hudi Unity Catalog

Spark ML XGBoost4J-Spark RAPIDS Evidently AI SageMaker Pipelines

FAISS Sentence-BERT Embeddings Multimodal RAG LangChain

AWS (Glue, Lambda, Athena, S3, SageMaker)
Azure (Databricks, Data Factory, Azure ML, DevOps)

.NET PostgreSQL Docker Flask API

• Processed 67M+ events
• Built batch + real-time analytics pipelines
• Apache Hudi → 50% faster queries, 40% less storage
• Kinesis + Flink + DynamoDB for DDoS/Bot detection

• XGBoost4J-Spark + RAPIDS Accelerator
• Production pipeline with SageMaker + Evidently AI
• Drift monitoring, CI/CD, orchestration

• Sentence-BERT embeddings
• FAISS vector retrieval
• Iceberg storage + Dockerized Flask API

• Text + Image embeddings
• FAISS vector indexing
• Streamlit app deployed on AWS

• Kafka + PySpark streaming joins
• Unity Catalog governance
• Azure DevOps CI/CD

Microsoft Certified: Azure Data Scientist Associate (DP-100)
https://learn.microsoft.com/en-us/users/prathy-0029/credentials/certification/azure-data-scientist

Python • PySpark • SQL • Spark ML • Kafka • Databricks • AWS • Azure • FAISS • Docker • PostgreSQL • PowerBI

I love working on:

• Distributed data systems
• ML at scale
• Vector search & RAG systems
• Streaming analytics

I enjoy translating complex data problems into scalable engineering systems.