Description

You design and build scalable data platforms and AI-driven solutions, owning the lifecycle from ingestion to intelligent automation.

This role is on-site.

Responsibilities

• Design and implement end-to-end data and AI systems, covering ingestion, analytics, and intelligent automation.
• Build agentic AI workflows using MCP, LangChain, and LangGraph for multi-agent orchestration.
• Develop and optimize data lakehouse architectures using Delta Lake, Iceberg, or Fabric Lakehouse.
• Implement ETL/ELT pipelines for structured, semi-structured, and unstructured data using Azure Data Factory or AWS Glue.
• Deploy ML models and establish MLOps/LLMOps pipelines for continuous monitoring and retraining.

Required Skills

• 5+ years of experience building scalable data and AI systems.
• Expert proficiency in Python, including Pandas, NumPy, Scikit-learn, and FastAPI.
• Advanced SQL skills with performance tuning and stored procedure development.
• Strong understanding of LLMs, embeddings, and vector stores (FAISS, Pinecone, Chroma).
• Hands-on experience building RAG pipelines and prompt engineering.
• Familiarity with agentic AI frameworks such as MCP, LangGraph, and LangChain Agents.
• Experience with data warehouse solutions like Snowflake, Azure Synapse, or BigQuery.
• Proficiency with orchestration tools including Azure Data Factory, AWS Glue, Databricks, or Fabric Pipelines.
• Experience working with Azure, AWS, or GCP cloud environments.

Preferred Skills

• Experience with unstructured data processing at scale.
• Contributions to open-source AI or data engineering projects.

Key Skills

Education

Any Graduate