Description

Design, develop, and deploy large-scale AI applications and LLM-based agents using Python, Java, and OpenShift.

This role is hybrid.

Responsibilities

• Design and build production-grade AI agents using Google ADK, Langgraph, and Langchain.
• Develop and maintain scalable applications using Java, Python, and OpenShift containers.
• Implement Retrieval Augmented Generation (RAG) systems, including vector stores, embeddings, and chunking strategies.
• Monitor model behavior, drift, and accuracy in production to ensure reliability and mitigate risk.
• Collaborate with enterprise teams to integrate LLM models with existing products and mentor junior engineers.

Required Skills

• 7+ years of software development experience with 5+ years in Python and/or Java.
• 3+ years of hands-on experience designing and deploying LLM-based applications.
• 3+ years of data engineering experience.
• 3+ years of AI/ML concepts, including deep learning, NLP, and computer vision.
• Experience with SDLC and Agile tools: Jira, GitHub, Jenkins, Confluence.
• Strong understanding of agent frameworks (Google ADK, Langgraph, Langchain).
• Bachelor's or Master's degree in Computer Science, AI, or related field.

Preferred Skills

• Advanced prompt engineering techniques (instruction design, few-shot, structured outputs).
• Experience with context management, memory handling, and guardrails for enterprise usage.
• Certification in AI or machine learning.

Key Skills

Education

Any Graduate