Open to opportunities

BASIL KISHORE

@basilkishore

Message

I build multi-cloud data platforms and production GenAI systems, from RAG chatbots to agent workflows.

India

Message

What I'm looking for

I'm looking to build production-ready, cost-efficient GenAI and agentic AI systems, data platforms, and MVPs that turn enterprise data into trusted decisions.

At Sopra Steria, I build production RAG, search, and Copilot systems alongside microservices that process millions of records each day for a nationwide user base.

I deployed a RAG chatbot on Azure using FastAPI, Azure Container Apps, PostgreSQL, and pgvector to deliver NLP-grounded Q&A over internal knowledge bases. I also built an enterprise RAG search and meeting-update agent system on Power Platform with Power Apps and SharePoint.

Previously at FREEKYAT SYSTEMS, I built an end-to-end AWS medallion data lake and CDC ingestion pipelines from Oracle GoldenGate through S3, Glue, PySpark, and Redshift. I optimized Spark workloads, implemented event-driven orchestration with Lambda and Step Functions, and enabled sub-second retrieval with OpenSearch.

I enjoy turning rough business ideas into MVPs and POCs that teams can evaluate and take into production. I'm currently focused on agentic AI workflows and making GenAI systems production-ready, cost-efficient, and grounded in enterprise data.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Engineer

Current

Sopra Steria

Nov 2024 - Present (1 year 10 months)

Built and deployed a production RAG chatbot on Azure: FastAPI on Azure Container Apps + PostgreSQL with pgvector for semantic search, enabling NLP-grounded conversational Q&A over internal knowledge bases.
Hands-on with Azure AI Foundry — model deployments, Foundry IQ service, Azure Functions, and Blob Storage for AI workload orchestration.

Worked within a microservices architecture processing mi

AWS Data Engineer

FREEKYAT SYSTEMS PRIVATE LIMITED

Oct 2021 - Nov 2024 (3 years 1 month)

Built an end-to-end medallion (bronze/silver/gold) data lake using AWS Glue, EMR, Lambda, and Step Functions.
Built a CDC-based ingestion pipeline: extracted Oracle data via Oracle GoldenGate (OGG) into S3 (JSON), processed with Glue/PySpark into a cleansed, partitioned raw zone, then a refined zone with business logic applied, then loaded into Redshift for downstream BI and analytics teams.

Impl

SQL / ETL DEVELOPER

FREEKYAT SYSTEMS PRIVATE LIMITED

Sep 2020 - Sep 2021 (1 year)

Extremely result-focused SQL and ETL developer with considerable experience extracting and transforming data via AWS Glue Studio for loading into S3, followed by loading into client-specific Redshift tables. Familiar with usage of Amazon Athena for analytics queries as well as Lambda functions to automate Glue jobs triggered by updates in S3.

Has experience in setting up CloudWatch for log monito