Senior Manager, AI Engineer Intelligence Layer

DataJobs; New York (NY); On-site; USD 190,000 - 210,000; Full time

Job summary

Alvarez and Marsal is building an Intelligence Layer in New York to make knowledge securely available for global and business-unit-specific search and AI experiences. You will design and deliver the knowledge graph platform from architecture to retrieval, APIs, and production agentic pipelines, in an onsite role.

The role emphasizes building ingestion pipelines, graph models, and APIs, with strong Python and backend skills, plus front-end collaboration as needed.

Qualifications

• Five or more years of software engineering experience building production applications or data platforms.
• Hands-on experience with knowledge graphs, graph data modeling, and graph query languages, ideally Neo4j and Cypher.
• Full-stack development experience with strong Python and back-end skills, plus working experience with a modern front-end framework.
• Experience designing, building, and consuming APIs and integrating multiple structured and unstructured data sources.
• Practical experience with Claude, ChatGPT, or comparable large language model platforms.
• Hands-on experience building production agentic pipelines or workflows, including orchestration, tool use, retrieval, state management, evaluation, guardrails, observability, or human oversight.
• Working knowledge of the Model Context Protocol, including MCP servers expose tools and data to AI clients.
• Experience working directly with third-party delivery vendors on implementation, technical review, issue resolution, and delivery coordination.
• Strong problem-solving, communication, and documentation skills.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Responsibilities

• Build and maintain components of the Intelligence Layer, including ingestion pipelines, knowledge graph models, retrieval services, APIs, and user-facing capabilities.
• Develop and optimize graph schemas and queries using Neo4j and Cypher (or comparable graph technologies).
• Contribute across the stack with strong Python and back-end development skills, while supporting modern front-end development when needed.
• Integrate structured data and unstructured content from enterprise systems while preserving source permissions, metadata, and governance requirements.
• Build integrations with large language model platforms and apply the Model Context Protocol (MCP) so Intelligence Layer capabilities can be used by approved AI tools.
• Build, test, and operate production agentic pipelines, including multi-step orchestration, tool routing, MCP-based tool use, retrieval, state management, evaluation, guardrails, observability, and human-in-the-loop controls.
• Partner with the Lead and Architect and delivery partners on implementation, testing, debugging, code review, and technical documentation.
• Develop secure, maintainable software that supports client confidentiality, access control, reliability, and observability.
• Communicate risks and blockers early and help the team make practical technical decisions as priorities evolve.
• Help deliver the initial production iteration of the Intelligence Layer knowledge graphs.
• Help deliver reusable agentic pipeline components for secure, governed workflows across business units and use cases.
• Enable global search and business unit specific search across approved structured and unstructured data sources.
• Deliver tested ingestion, graph, retrieval, API, and user-interface components that internal teams can operate and extend.
• Establish reusable engineering patterns and documentation that support additional business units and data sources.

Skills

Knowledge graphs

Cypher

Neo4j

Python

APIs

LLMs

Azure

OAuth 2.0

OpenID Connect

Model Context Protocol

Entra ID

MCP

Education

Bachelor’s degree in CS/Engineering or related field

Tools

Front-end framework

Job description

Alvarez and Marsal is building an Intelligence Layer that makes the firm’s knowledge securely available for global and business-unit-specific search and AI experiences. In this onsite role in New York, you will help design and deliver the knowledge graph platform, working from architecture and ingestion through retrieval, APIs, and production agentic pipelines.

What you will do

• Build and maintain components of the Intelligence Layer, including ingestion pipelines, knowledge graph models, retrieval services, APIs, and user-facing capabilities.
• Develop and optimize graph schemas and queries using Neo4j and Cypher (or comparable graph technologies).
• Contribute across the stack with strong Python and back-end development skills, while supporting modern front-end development when needed.
• Integrate structured data and unstructured content from enterprise systems while preserving source permissions, metadata, and governance requirements.
• Build integrations with large language model platforms and apply the Model Context Protocol (MCP) so Intelligence Layer capabilities can be used by approved AI tools.
• Build, test, and operate production agentic pipelines, including multi-step orchestration, tool routing, MCP-based tool use, retrieval, state management, evaluation, guardrails, observability, and human-in-the-loop controls.
• Partner with the Lead and Architect and delivery partners on implementation, testing, debugging, code review, and technical documentation.
• Develop secure, maintainable software that supports client confidentiality, access control, reliability, and observability.
• Communicate risks and blockers early and help the team make practical technical decisions as priorities evolve.
• Help deliver the initial production iteration of the Intelligence Layer knowledge graphs.
• Help deliver reusable agentic pipeline components for secure, governed workflows across business units and use cases.
• Enable global search and business unit specific search across approved structured and unstructured data sources.
• Deliver tested ingestion, graph, retrieval, API, and user-interface components that internal teams can operate and extend.
• Establish reusable engineering patterns and documentation that support additional business units and data sources.

First-year outcomes

• Deliver the initial production iteration of the Intelligence Layer knowledge graphs.
• Deliver reusable agentic pipeline components supporting secure, governed workflows across business units and use cases.
• Enable global search and business unit specific search across approved structured and unstructured data sources.
• Ship tested ingestion, graph, retrieval, API, and user-interface components internal teams can operate and extend.
• Establish reusable engineering patterns and documentation to support additional business units and data sources.

Required qualifications

• Five or more years of software engineering experience building production applications or data platforms.
• Hands-on experience with knowledge graphs, graph data modeling, and graph query languages, ideally Neo4j and Cypher.
• Full-stack development experience with strong Python and back-end skills, plus working experience with a modern front-end framework.
• Experience designing, building, and consuming APIs and integrating multiple structured and unstructured data sources.
• Practical experience with Claude, ChatGPT, or comparable large language model platforms.
• Hands-on experience building production agentic pipelines or workflows, including orchestration, tool use, retrieval, state management, evaluation, guardrails, observability, or human oversight.
• Working knowledge of the Model Context Protocol, including how MCP servers expose tools and data to AI clients.
• Experience working directly with third-party delivery vendors on implementation, technical review, issue resolution, and delivery coordination.
• Strong problem-solving, communication, and documentation skills.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Preferred qualifications

• Hands-on experience building MCP servers, agent tools, or custom AI integrations.
• Experience with Microsoft Azure services for application hosting, data, search, identity, or AI.
• Experience implementing enterprise authentication and authorization using Microsoft Entra ID, OAuth 2.0, OpenID Connect, token scoping, or on-behalf-of flows.

Technologies

• Neo4j, Cypher, Python
• Claude, ChatGPT, Model Context Protocol, MCP servers, large language model platforms
• Microsoft Azure
• Microsoft Entra ID, OAuth 2.0, OpenID Connect
• Token scoping, on-behalf-of flows

Compensation

The salary range is $190,000 - $210,000 annually, dependent on education, experience, skills, and geography. A discretionary bonus program may also be available based on individual and firm performance.

Benefits

• Healthcare plans
• Flexible spending and savings accounts
• Life, AD&D, and disability coverages
• 401(k) retirement savings plan
• Annual discretionary contribution to their 401(k) retirement savings plan
• Paid time off including vacation, personal days, seventy-two (72) hours of sick time (prorated for part time employees), ten federal holidays, one floating holiday, and parental leave