Job Title

Role SummaryAs the Lead AI/ML Engineer (Agentic Systems), you will architect and deliver production-grade autonomous AI workflows that go well beyond conversational assistants. This role sits at the intersection of software engineering, data engineering, and machine learning engineering, building stateful, goal-driven AI systems that can reason, plan, coordinate, and execute complex tasks with appropriate controls.Responsibilities1) Agentic Systems Architecture & Core EngineeringDesign and build multi-agent workflows: Lead hands-on engineering of stateful agentic applications using agent orchestration frameworks capable of coordinating multiple autonomous components.Agent-to-agent collaboration: Define and implement robust communication patterns that allow agents to delegate sub-tasks, negotiate execution paths, and coordinate outcomes in dynamic environments.State, memory, and long-running execution: Engineer control flows for non-deterministic systems, including message passing, persistent memory, recoverability, and interruptible execution for long-running tasks.Standardized tool interfaces: Establish universal interfaces between agents, enterprise data sources, and operational tools to ensure modularity, reusability, and consistent governance.Model integration and runtime optimization: Build routing and fallback strategies across multiple model endpoints; optimize context management, latency, and inference cost while maintaining reliability.Production deployment: Package and deploy workloads via containerization and cluster orchestration, using cloud-native services for scaling, isolation, and secure runtime operations.2) Data Engineering & Operational Real-Time IntegrationBuild agent-ready data pipelines: Develop and maintain high-throughput ingestion and transformation pipelines that convert raw operational signals into structured, machine-consumable context.Real-time context injection: Ensure agents can access near-real-time operational data by designing efficient retrieval patterns and optimizing vector databases and associated retrieval architectures.Cross-functional execution: Serve as the technical bridge between AI and data teams—translating agent needs into schemas, data contracts, SLAs, and pipeline specifications, while resolving bottlenecks hands-on.3) Observability, Governance & Human-in-the-LoopLLMOps, tracing, and debugging: Implement end-to-end observability for agent execution, including reasoning traces, performance telemetry, cost monitoring, and production debugging workflows.Safety and control frameworks: Design hybrid autonomy modes (human-in-the-loop through fully autonomous), including approval gates, policy enforcement, and “break-glass” controls for sensitive operations.Evaluation and reliability standards: Establish rigorous testing strategies for stochastic systems; automate evaluation pipelines to measure accuracy, failure modes, drift, and regression risk prior to deployment.4) Technical Leadership & StrategyDefine the agentic architecture roadmap: Partner with product and engineering leadership to scope feasibility, set technical direction, and prioritize high-impact autonomous initiatives.Mentorship and engineering standards: Set expectations for code quality, architectural patterns, and review processes; mentor engineers to level up agentic engineering practices.Innovation to production: Rapidly prototype emerging approaches (e.g., advanced retrieval strategies, graph-based reasoning patterns) and mature successful experiments into supported production capabilities.QualificationsRequiredExperience: 7+ years in software engineering, data engineering, and/or machine learning engineering, with demonstrated ownership of production systems.Generative AI in production: 2+ years building and deploying LLM-based applications and/or agentic systems in real-world environments.Storage and retrieval expertise: Proven experience designing AI-ready storage layers across vector databases, relational and NoSQL databases, and modern lakehouse/warehouse architectures.Cloud and infrastructure depth: Strong capability deploying and scaling services on major cloud platforms using containerization, cluster orchestration, CI/CD, and secure runtime practices.LLM systems understanding: Strong grasp of retrieval-augmented generation, embeddings, context strategies, prompt/system design, and failure modes in deployed systems.Hybrid engineering skillset: Ability to blend ML intuition (model behavior, uncertainty, evaluation) with software excellence (APIs, async systems, reliability engineering).Programming: Advanced proficiency in Python for building modular, testable, maintainable production services.Education: Bachelor’s degree in Computer Science, Engineering, Mathematics, or related technical field (or equivalent experience).PreferredAdvanced degree: Master’s or PhD in AI, Computer Science, or another quantitative discipline.Deep NLP experience: Extensive applied NLP background spanning classical methods through modern large-model applications.Graph-based reasoning: Experience with knowledge graphs / graph databases and graph machine learning to support multi-step reasoning and relationship-driven workflows.Agentic specialization: Prior implementation of multi-agent coordination, advanced tool-use patterns, and standardized agent-tool integration approaches.Real-time operational environments: Background in domains requiring seconds-to-minutes latency decision support (e.g., energy, logistics, financial systems).Why This Role MattersThis role defines how S&P Global Energy moves from static analytics to active, autonomous decision workflows. You will help build an AI “operating layer” that can sense changing conditions, plan actions, coordinate across specialized agents, and execute safely—with the observability, governance, and reliability required for production. The systems you deliver will become foundational infrastructure: a strategic capability that changes how work is performed, scaled, and controlled across the organization.What’s In It For You?Our Mission: Advancing Essential Intelligence.Our People:We're more than 35,000 strong worldwide—so we're able to understand nuances while having a broad perspective. Our team is driven by curiosity and a shared belief that Essential Intelligence can help build a more prosperous future for us all.From finding new ways to measure sustainability to analyzing energy transition across the supply chain to building workflow solutions that make it easy to tap into insight and apply it. We are changing the way people see things and empowering them to make an impact on the world we live in. We’re committed to a more equitable future and to helping our customers find new, sustainable ways of doing business. Join us and help create the critical insights that truly make a difference.