Description

You will build and maintain agentic AI solutions, data pipelines, and LLM integrations for enterprise systems.

You will own the end-to-end development of GenAI data infrastructure, from ingestion to orchestration.

Responsibilities

• Develop agentic AI solutions using Google ADK, LangChain, and LangGraph, implementing orchestration and tool usage patterns.
• Build and optimize ETL/ELT pipelines to integrate data from APIs, databases, files, and streams.
• Design and implement RAG architectures, integrating LLMs with vector stores and relational systems.
• Write advanced SQL queries and ensure data quality, schema evolution, and lineage tracking.
• Apply production-grade engineering practices including testing, CI/CD, logging, monitoring, and error handling.

Required Skills

• 5+ years in GenAI, AI Data Engineering, or Agentic AI roles.
• Advanced Python development for backend services, workflow engines, and AI pipelines.
• Hands-on experience with Google ADK, LangChain, and LangGraph.
• Advanced prompt engineering and context engineering skills.
• Strong data engineering expertise: ETL/ELT, multi-source integration, and data governance.
• Advanced SQL proficiency (complex joins, window functions, query optimization).
• Experience with RAG architectures and enterprise LLM integration.

Preferred Skills

• Experience with modern data stack tools: dbt, Airflow/Composer, Kafka/PubSub, BigQuery/Snowflake.
• Familiarity with vector databases, hybrid retrieval, and LLMOps frameworks.
• Experience deploying scalable solutions on GCP or other cloud platforms.

Key Skills

Education

Bachelor's degree