Job Summary
The Agentic AI Developer will design, develop, and implement enterprise-grade agentic AI solutions and multi-agent systems. The role requires strong expertise in Python, Large Language Models (LLMs), AI orchestration frameworks, knowledge retrieval systems, and enterprise application integration. The developer will build intelligent agents capable of planning, reasoning, interacting with external tools, and coordinating with other agents while ensuring security, governance, observability, and compliance. The role also involves establishing evaluation frameworks, optimizing agent performance, and translating business objectives into scalable AI solutions.
Key Responsibilities
• Design and develop multi-agent architectures for enterprise AI applications.
• Build tool-calling capabilities and API integrations for AI agents.
• Implement planning, reasoning, and workflow orchestration mechanisms.
• Manage agent memory, context, and Retrieval-Augmented Generation (RAG) patterns.
• Develop and coordinate agent-to-agent communication mechanisms.
• Implement observability, evaluation frameworks, performance monitoring, and guardrails for agentic AI systems.
• Ensure security, governance, and compliance for autonomous agent actions.
• Integrate AI agents with enterprise applications, APIs, databases, and external services using MCP (Model Context Protocol) and function-calling architectures.
• Design and implement knowledge retrieval systems using vector databases, embeddings, semantic search, and enterprise knowledge repositories.
• Establish evaluation, tracing, benchmarking, and continuous improvement processes to ensure reliable agent behavior and quality outcomes.
• Monitor and optimize AI agent performance through testing and performance improvement initiatives.
• Implement change management processes to maintain consistent, reliable, and maintainable software versions.
• Translate business objectives into scalable AI solutions and support adoption through measurable business outcomes.
• Apply AI governance, security controls, model risk management, data privacy, and responsible AI practices.
Required Qualifications
• 5+ years of software development experience.
• Demonstrated expertise in Python and modern software engineering practices.
• Experience with API development, distributed systems, version control, testing frameworks, and CI/CD automation.
• Deep understanding of LLM architectures, prompt engineering, context management, model selection, and optimization techniques for enterprise-grade AI solutions.
• Experience designing and implementing knowledge retrieval systems using vector databases, embeddings, semantic search, and enterprise knowledge repositories.
• Proficiency with agentic AI frameworks and orchestration platforms for multi-agent coordination and workflow automation.
• Experience integrating AI agents with enterprise applications, APIs, databases, and external services using MCP and function-calling architectures.
• Experience establishing evaluation frameworks, performance monitoring, tracing, benchmarking, and continuous improvement processes.
• Strong understanding of AI governance, security controls, model risk management, compliance requirements, data privacy, and responsible AI practices in regulated environments.
• Experience with performance testing and optimization.
• Ability to develop and follow change management processes for consistent and maintainable version control.
• Ability to translate business objectives into scalable technical solutions.
• Excellent written and verbal communication skills.
• Willingness to collaborate across different time zones.
Preferred Qualifications
• Exposure to the financial services industry.
