Description

Key Responsibilities

• Develop GenAI-powered solutions for natural language business questions and data analysis.
• Implement Text-to-SQL and Text-to-Code capabilities.
• Build RAG-based solutions using enterprise data, metadata, business definitions, and documentation.
• Develop AI agents or agentic workflows for:

 Dataset discovery

 SQL generation

 Code generation

 Data validation

 Code validation

 Output validation

• Integrate LLMs with enterprise data platforms and APIs.
• Build data processing and analytics workflows using Python and SQL.
• Develop data quality and validation frameworks.
• Automate data and AI workflows using cloud-native services.
• Create and maintain Infrastructure as Code using Terraform or CloudFormation.
• Build CI/CD pipelines for AI and data workloads.
• Implement monitoring, logging, and observability.
• Support deployment of GenAI solutions across development, test, and production environments.
• Work closely with the Architect and Full-Stack teams to integrate AI capabilities into the platform.

Required Skills

• 6–10+ years of experience in AI/ML, Data Engineering, or Software Engineering.
• Strong hands-on experience with GenAI and LLM applications.
• Experience with RAG, prompt engineering, AI agents, or Agentic AI.
• Strong Python and SQL skills.
• Experience with data analytics and data processing.
• Experience with AWS cloud services.
• Experience with Amazon Bedrock or equivalent LLM platforms.
• Strong understanding of APIs and AI integration.
• Experience with Terraform / Infrastructure as Code.
• Experience with CI/CD and DevOps.
• Knowledge of data governance and security.

Preferred

• Experience with LangChain, LangGraph, or similar frameworks.
• Experience with vector databases.
• Experience with AWS Glue, Athena, S3, Redshift, or similar.
• Experience building AI-powered analytics or Text-to-SQL solutions

Key Skills

Education

Bachelor's degree