AI Engineering Lead – Agentic Systems

Role Overview As Tech Lead, Agentic AI Solutions, you will lead the design and delivery of enterprise-grade agentic AI architectures that enable autonomous and semi-autonomous agents to perform complex, cross-functional business tasks. You will define the frameworks, orchestration patterns, and governance standards that ensure our agentic AI systems operate with safety, reliability, and scalability across enterprise environments. This position blends deep technical leadership with innovation in AI orchestration, distributed systems, and multi-agent coordination. This is an ideal opportunity for an experienced technologist who thrives in a dynamic environment and is passionate about shaping the next generation of intelligent agent platforms within the enterprise. Key Responsibilities Architect & Lead Development : Design and implement scalable agentic AI frameworks, including multi-agent orchestration, task planning, and execution pipelines. Integration & Protocol Design : Architect secure protocols and integrations—such as Model Context Protocol (MCP) servers, API gateways, and tool registries—to enable seamless agent-to-agent and agent-to-human collaboration. Technical Roadmap Ownership : Define and execute the roadmap for agentic AI solutions, continuously evaluating and adopting emerging frameworks like LangGraph, Bedrock Agents, CrewAI, and Strands. Reusable Registries : Establish governed agent, prompt, and tool registries for standardized, reusable components. Reliability & Performance : Engineer high-reliability orchestration with low latency, intelligent fallback, and self-healing mechanisms. Observability & Governance : Implement traceability, explainability, and observability tools to ensure transparent, auditable agentic workflows. Security & Compliance : Define security standards for API access, RBAC, data sanitization, and policy-gated tool execution; ensure compliance with NIST AI RMF, ISO / IEC 42001, and privacy-by-design principles. Monitoring & Evaluation : Develop real-time monitoring pipelines that track agent decision quality, execution success / failure, and dependency health. Cross-Functional Collaboration : Partner with Product Managers, Data Engineers, Legal / Compliance, and Business stakeholders to translate strategic objectives into robust agentic capabilities. Innovation : Advance methods in planning, memory, context engineering, and knowledge integration to enhance autonomy, reliability, and reasoning capabilities. Technical Leadership : Mentor engineers, promote best practices in AI infrastructure, and guide teams in developing modular, scalable, and compliant agentic systems. Required Qualifications Education : Bachelor’s degree in Computer Science, Engineering, or related technical field (or equivalent practical experience). Experience : 8+ years of software engineering experience in AI / ML, distributed systems, or platform engineering. 3+ years in senior technical leadership or architecture roles guiding multi-disciplinary teams. Technical Expertise : Strong proficiency in Python and experience with multiple programming paradigms. Deep experience with the AWS ecosystem (Bedrock, SageMaker, Lambda, S3, Redshift, VPC). Proven ability to design agent-safe protocols (MCP, API sandboxes, secure tool registries). Expertise in distributed systems, asynchronous processing, and low-latency orchestration. Hands-on experience with AI observability and traceability systems. Familiarity with metadata management, data lineage, and knowledge graph integration for agent context enhancement. Leadership & Governance : Skilled in agile methodologies and iterative delivery of complex AI infrastructure. Demonstrated success implementing AI governance and compliance frameworks. Exceptional ability to communicate complex technical concepts to both engineers and executives. Strong track record of mentoring, team building, and fostering inclusive, high-performing teams. Preferred Qualifications Experience with LangChain, LangGraph, Bedrock Agents, CrewAI, or LLMOps frameworks. Knowledge of GraphRAG, memory management, and context-aware planning in multi-agent systems. Exposure to regulated environments such as healthcare, finance, or aviation. Familiarity with AI risk management, auditability frameworks, and policy-driven AI governance.