Description

Design and implement RAG pipelines, optimizing document retrieval and embedding strategies for scalable AI solutions.

This role is on-site.

Responsibilities

• Build RAG pipelines using hybrid search, vector keyword semantic ranking, and metadata enrichment.
• Apply fixed size, recursive, semantic, and agentic chunking strategies to optimize document segmentation.
• Collaborate with stakeholders to translate business needs into reliable, performant, and ethically compliant AI deployments.
• Ensure model reliability and performance across all production environments.

Required Skills

• 7+ years of experience as a Fullstack developer.
• 2-4 years of hands-on experience in Generative AI or RAG systems.
• Proficiency in Python.
• Deep understanding of chunking techniques and embedding strategies.
• Experience with MLOps tools, specifically MLflow.
• Proficiency with Docker and CI/CD pipelines.
• Strong skills in prompt engineering and model evaluation.

Preferred Skills

• Familiarity with Agentic Systems.
• Experience with Multi-Agent Orchestration.

Key Skills

Education

Bachelor's degree