RCI-BDX-3331 Software Engineer / Data Engineer (Databricks/RAG/LLM/GraphRag/SalesForce/SAP/Python/SQL) (Medical Device)

Rangam is a company focused on innovative solutions in the medical device sector, and they are seeking a Software Engineer / Data Engineer with expertise in Databricks and AI development. The role involves designing and optimizing data pipelines, processing unstructured data, and collaborating with cross-functional teams to create scalable data solutions.

Responsibilities:

• Design, build, and optimize medallion architecture pipelines (Bronze → Silver → Gold) in Databricks using Delta Lake
• Ingest and process unstructured data (PDFs, images, documents, logs) from enterprise source systems (SAP, Salesforce, TrackWise, Azure DevOps, etc.)
• Curate and model data into structured, query-ready schemas to power AI agents and analytics applications
• Develop and maintain data quality frameworks, validation checks, and monitoring across pipeline stages
• Collaborate with AI/ML engineers to prepare datasets for LLM-powered agents (Claude, GPT) including embeddings, chunking strategies, and retrieval-augmented generation (RAG) pipelines
• Support Unity Catalog governance, access controls, and schema management across dev/prod workspaces
• Partner with cross-functional teams (Quality, Regulatory, IT, R&D) to translate business requirements into scalable data solutions

Requirements:

• Databricks Mosaic AI
• Databricks SQL
• Databricks Unity Catalog
• GraphRag
• SalesForce
• SAP
• 7+ years of hands-on experience with Databricks (Delta Lake, Spark, SQL, Python)
• Proven experience implementing medallion architecture (Bronze → Silver → Gold) at scale
• Strong expertise working with unstructured data — parsing, transforming, and curating documents, PDFs, and text into structured data models
• Experience building data pipelines that feed AI/ML agents or LLM-based applications
• Working knowledge of Claude (Anthropic) and GPT (OpenAI) model integration, prompt engineering, or agent orchestration
• Proficiency in Python and SQL; experience with Databricks notebooks, workflows, and jobs
• Solid understanding of data modeling best practices for analytics and AI consumption