Description

You will design and maintain data infrastructure while integrating large language models into production systems.

This role is on-site.

Responsibilities

• Build and optimize ETL/ELT pipelines using Python, Java, SQL, and BigQuery.
• Implement RAG pipelines, prompt engineering, and LLM integrations on GCP.
• Develop data models and manage vector databases for AI applications.
• Troubleshoot production issues and tune performance for data workflows.
• Communicate technical requirements with stakeholders to align on deliverables.

Required Skills

• 8+ years of experience in Data Engineering or Software Engineering.
• Strong proficiency in SQL and BigQuery or equivalent data warehouses.
• Expertise in Python and/or Java.
• Hands-on experience with GCP services: BigQuery, Airflow, Dataflow, Pub/Sub.
• Practical knowledge of LLMs, Prompt Engineering, and RAG architectures.
• Solid understanding of data modeling and performance tuning.
• Proven track record of handling production incidents in fast-paced environments.

Preferred Skills

• Experience with OpenAI/Claude APIs and Model Context Protocol (MCP).
• Background in financial reconciliation or AI usage analytics.

Key Skills

Education

Not specified