Description

You will build and deploy multi-modal data pipelines handling text, image, and unstructured data.

This role is on-site.

Responsibilities

• Develop and implement Retrieval Augmented Generation (RAG) solutions utilizing vector databases.
• Design and maintain data processing workflows using big data frameworks and streaming pipelines.
• Integrate and guide teams on GenAI and LLM functionalities within production systems.
• Collaborate with data engineering and applied AI/ML teams to deliver ML solutions.

Required Skills

• 7+ years of professional experience.
• Expert proficiency in Python, with strong OOPs understanding.
• Hands-on experience with PySpark and Scala.
• Proven ability to use LangChain and LangGraph for LLM applications.
• Experience with cloud data platforms and multi-modal embedding techniques.
• Familiarity with containerization (Docker) and orchestration tools like Airflow or Dagster.
• Proficiency in version control using Git and tracking issues in JIRA.
• Familiarity with testing frameworks such as Pytest.

Key Skills

Education

Any Graduate