Description

You will build and deploy LLM-based applications and RAG pipelines using vector databases for enterprise knowledge retrieval.

This role is on-site.

Responsibilities

• Develop and optimize data pipelines for structured and unstructured datasets to support LLM and agent workflows.
• Engineer prompts, system instructions, and memory architectures for domain-specific reasoning.
• Evaluate model performance, focusing on accuracy, hallucination mitigation, latency, and safety compliance.
• Build backend services for AI applications using Python.
• Deploy and productionize AI solutions on Azure Data & AI Services.

Required Skills

• 6+ years of overall software engineering experience.
• Strong hands-on experience with Generative AI and Large Language Models (LLMs).
• Proficiency in Python backend development.
• Experience building RAG pipelines and working with vector databases.
• Expertise in prompt engineering and system instruction design.
• Experience with Azure Data & AI Services.

Preferred Skills

• Experience developing AI agent-based solutions.
• Proven track record of deploying and productionizing AI solutions.
• Skills in unstructured data processing and optimization.

Key Skills

Education

Bachelor's degree