Agentic AI Data Engineer
Experience: 5–10 Years
Location: Gurgaon / Pune (first priority), Noida, Bangalore, Hyderabad, Chennai
Role Overview
We are seeking an Agentic AI Data Engineer with expertise in AWS, Python, SQL, and PySpark to build scalable AI-powered data platforms and intelligent automation solutions. The ideal candidate will have hands-on experience with LLMs, RAG, agentic AI frameworks, cloud-native architectures, and modern data engineering practices.
Key Skills: (priority-wise)
- Amazon Sagemaker or Bedrock
- LangGraph,AutoGen, LangChain
- LLM Orchestration & Prompt Engineering
- RAG, , agentcore, agent frameworks
- Python, SQL
Responsibilities
- Design and develop Agentic AI and LLM-powered applications using RAG, multi-agent frameworks, and vector databases.
- Build and optimize scalable ETL/ELT pipelines for structured and unstructured data using Python, PySpark, and SQL.
- Develop APIs and integrate AWS services such as S3, Glue, Lambda, SageMaker, Bedrock, and Redshift into enterprise AI solutions.
- Implement data lakes, lakehouse architectures, and real-time data processing using Spark, Kafka/Kinesis, and cloud-native services.
- Ensure data quality, governance, security, monitoring, and performance optimization across AI and data platforms.
- Collaborate with data scientists, ML engineers, and product teams to deliver reliable, production-grade AI solutions.