We are seeking an AI Engineer to design, implement, and operationalize artificial intelligence solutions across the firm, with a particular focus on building a modern, MCP-enabled AI integration layer that connects models securely to enterprise data and tools. This role will be responsible for developing the core AI infrastructure, agents, and integration patterns that enable scalable use of generative and predictive AI across research, investment, and operational teams.
The ideal candidate blends strong software engineering skills with applied machine learning experience, deep familiarity with LLM and agentic patterns, and hands-on experience implementing standards such as the Model Context Protocol (MCP) in an enterprise environment.
Key Responsibilities
• Design, build, and deploy AI models, tools, and agents to automate intelligence-heavy workflows in investment research, portfolio management, operations, and client reporting.
• Partner with the Head of Data & AI to define the technical architecture for AI use cases, integrating with Snowflake, Databricks, internal APIs, and event streams in a secure and governed way.
• Implement retrieval augmented generation (RAG) pipelines and prompt conditioning patterns that ground LLMs on Marathon’s proprietary data, documents, and knowledge assets.
• Design and implement Model Context Protocol (MCP)–based integrations so AI assistants and agents can securely discover and connect to internal systems, databases, and services through standardized MCP servers and clients.
• Build and maintain MCP servers that wrap key enterprise services (data warehouses, document stores, workflow systems) and expose tools, resources, and prompts to AI clients in a standardized way.
• Establish patterns for MCP host/client configuration, access control, and observability to ensure reliable, auditable AI interactions with enterprise systems.
• Implement MLOps and LLMOps practices for both model and MCP-based integration lifecycles, including deployment automation, monitoring, logging, and rollback strategies.
• Collaborate with data engineers and platform teams to ensure clean, secure, and well-structured data access for AI consumption, including governance of which systems are exposed via MCP.
• Evaluate and integrate external AI platforms (e.g., Azure OpenAI, Anthropic, others) and assess when to use native tool APIs versus MCP-standardized integrations.
• Develop proofs of concept (POCs), productionize successful solutions, and document reusable patterns, SDKs, and templates for AI and MCP usage firm wide.
• Ensure all AI and MCP solutions meet enterprise security, privacy, and compliance standards, including identity and access management, data residency, and vendor risk management.
• Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, or a related field; advanced degree preferred.
• 5–8+ years’ experience in software engineering or ML/AI engineering, ideally including work in financial services, asset management, or other regulated industries.
• Strong proficiency in Python and common AI/ML and LLM frameworks (e.g., PyTorch, TensorFlow, LangChain, LlamaIndex, Hugging Face).
• Hands on experience designing and deploying LLM based applications, including RAG, tool calling, and agent frameworks.
• Practical experience with Model Context Protocol (MCP) or similar standardized integration approaches for connecting LLMs to external tools, data sources, and workflows (e.g., building MCP servers/clients, configuring hosts, managing tools and resources).
• Familiarity with modern data and ML platforms, and orchestration tools.
• Experience with APIs, microservices, and containerization (REST, gRPC, Docker, Kubernetes) and with securing integrations across internal and SaaS environments.
• Working knowledge of cloud-based AI/ML services (Azure) and associated security and networking patterns.
• Excellent communication and collaboration skills, with the ability to translate between technical detail, business value, and risk considerations.
Python, AI/ML frameworks (PyTorch, TensorFlow), LLM frameworks (LangChain, LlamaIndex, Hugging Face), Large Language Model (LLM) application development, Retrieval Augmented Generation (RAG), Prompt engineering and prompt conditioning, Agent frameworks and tool calling, Model Context Protocol (MCP), MCP server and client development, AI integration architecture, Snowflake, Databricks, API integration, Event stream integration, MLOps, LLMOps, Data engineering collaboration, Cloud AI/ML services (Azure), Microservices architecture, REST APIs, gRPC, Docker, Kubernetes, Enterprise system integration, Security and access control, Observability and monitoring, Deployment automation, Logging and rollback strategies, Proof of Concept (POC) development, AI platform integration (Azure OpenAI, Anthropic), Enterprise data governance, Identity and access management, Compliance and security standards.