Responsibilities

• Build AI agents using frameworks like LangGraph, Autogen, Crew, or PydanticAI
• Design and optimize prompt engineering workflows for LLMs such as GPT, Claude, and LLaMA
• Develop modular and reusable components for agent orchestration and automation
• Deploy AI models using Databricks and Azure environments such as ARO and AKS
• Collaborate with platform teams to ensure scalable, secure deployments
• Implement APIs and support real-time systems using event-driven architecture
• Work with CI/CD pipelines using Jenkins for automated deployments
• Maintain code quality and documentation using Git, Jira, and Confluence

Required Skills

• 3 to 5 years of experience in Machine Learning, Artificial Intelligence, or related domains
• Minimum 1 year of experience building enterprise-grade Generative AI applications
• Strong understanding of RAG workflows and LLM-based systems
• Proficiency in Python and modern development practices
• Hands-on experience with prompt engineering and LLM integration
• Experience with Databricks and cloud-native deployments
• Understanding of REST APIs, WebSockets, and event-driven systems
• Experience with CI/CD tools such as Jenkins and version control systems like Git
• Familiarity with SDLC processes and agile methodologies
• Knowledge of enterprise security, compliance, and governance in AI systems

Mandatory Skills

Generative AI + LLM + RAG     AI Agent frameworks     Python, Databricks