Durapid Technologies

Role Description We are seeking a highly experienced and forward-thinking Agentic AI Architect to design and build next-generation AI systems for the banking and financial services sector. This role focuses on moving beyond static prompts into dynamic planning, reasoning, and autonomous execution—while ensuring strict compliance, security, and reliability required in financial environments. You will own end-to-end architecture for mission-critical AI systems in a high-impact, high-visibility setting. Key Responsibilities - Design and implement end-to-end architectures for agent-based AI systems tailored to banking use cases (e.g., underwriting, fraud detection, customer servicing, risk analysis) - Architect scalable and secure MLOps / LLMOps pipelines aligned with financial regulatory standards - Define frameworks for multi-agent coordination, including planning, memory, tool usage, and inter-agent communication - Design and implement Agent-to-Agent (A2A) communication protocols for distributed financial intelligence systems - Leverage Model Context Protocol (MCP) to standardize secure tool access, auditability, and context sharing across agents - Translate complex financial business problems into production-grade AI system designs with measurable outcomes - Evaluate and evolve the AI technology stack, including agentic frameworks (such as LangChain, LangGraph, Google ADK), orchestration layers, vector databases, and secure infrastructure - Ensure AI governance, explainability, audit trails, and compliance with regulatory requirements (e.g., model risk management, data privacy) - Build systems with strong observability, monitoring, and fail-safe mechanisms for high-stakes environments - Collaborate with business, risk, compliance, and technology teams to align AI capabilities with banking strategy - Mentor engineering teams and guide architectural decisions across AI initiatives Qualifications - 8+ years of experience in AI/ML systems, distributed systems, or enterprise architecture - Strong experience in banking, financial services, or fintech environments - Deep expertise in Large Language Models (LLMs) and real-world deployment in regulated industries - Strong programming expertise in Python for building scalable AI systems and services - Hands-on experience with cloud platforms (AWS, GCP, Azure) and secure infrastructure design - Proven experience in building and managing MLOps / LLMOps pipelines with governance controls - Strong experience with agentic AI frameworks, including LangChain, LangGraph, and/or Google ADK - Hands-on exposure to Agent-to-Agent (A2A) communication patterns and distributed agent coordination - Experience working with Model Context Protocol (MCP) or similar standards for secure tool integration and context management - Solid understanding of microservices, event-driven architectures, APIs, and data pipelines - Experience with vector databases, retrieval-augmented generation (RAG), and memory systems - Strong understanding of financial data security, privacy, and compliance requirements - Ability to think in systems: abstraction, trade-offs, scalability, and long-term evolution