Data Engineer 2

• Develop and maintain scalable data pipeline using Snowflake and Azure ecosystem
• Implement high quality data ingestion and transformation frameworks for structured and unstructured data
• Develop Gen AI solutions using LLMs, including RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases
• Build and optimize embedding pipelines and vector search solutions for semantic retrieval
• Create standard processes and metric definitions for optimized analytics, reporting and downstream consumption
• Create and execute unit testing and end-to-end integration test plans for each block of data and analytics pipelines.
• Optimize performance of data pipelines and queries to meet SLAs

Must‑Have Qualifications

• 2-4 years total experience in data engineering on cloud platforms, with Applied AI.
• Min 2 years of experience in Snowflake with exposure to warehouse configuration, schema design, performance tuning; stored procedures/tasks; loading strategies. Exposure to Snowflake Cortex AI.
• Experience working on Azure cloud platform and ADLS.
• Experience in building Gen AI solutions using LLMs, RAG pipelines, vector DBs and embeddings.
• SQL/Python/PySpark: Design and implement scalable data processing solutions using SQL, Python, and distributed compute frameworks, including unit/integration tests.
• Built and deployed RESTful APIs for data ingestions, Gen AI applications and LLM inference endpoints for internal workflows.
• Version control & CI/CD: Exposure to Git, pull requests, automated deployment pipelines.
• Maintain a results-oriented mindset with strong analytical and problem-solving skills.
• Strong communication and collaboration skills to work in an Agile and global setting.
  • Good to have: Experience in Healthcare Industry