Description

Key Responsibilities:
• Build high-volume data pipelines (batch & near real-time)
• Develop LLM-based extraction & processing workflows
• Implement validation layers to reduce hallucinations
• Design end-to-end data architecture (ingestion to serving)
• Work on embeddings, vector search & retrieval systems
• Ensure data quality, observability & system reliability

Core Skills:
• Strong Python & backend/data engineering experience
• Hands-on with ETL/streaming pipelines
• Experience with LLMs in production (prompting, validation, monitoring)
• Knowledge of distributed systems & failure handling
• SQL + NoSQL databases
• Cloud experience (AWS preferred)

Nice to Have:
• RAG / vector search experience
• Financial domain exposure
• Kafka / streaming systems
• Agentic or multi-step AI workflows

Key Skills

Education

Bachelor's degree