AI Engineer

Madison-Davis, LLC; New York (NY); On-site; USD 140,000 - 210,000; Full time

Job summary

Madison-Davis, LLC in New York is expanding an AI technology team responsible for building the shared infrastructure behind enterprise AI applications. The team is moving beyond isolated experimentation and creating a scalable platform that enables engineers and business teams to develop, deploy, evaluate, and operate AI agents in production.

This engineer will own meaningful pieces of that platform end-to-end.

Qualifications

• Strong software-engineering background with hands-on development experience.
• Experience building AI-enabled applications, agentic workflows, or LLM infrastructure.
• Hands-on experience with RAG or enterprise-retrieval architectures.
• Understanding of securely exposing proprietary datasets to AI applications.
• Experience designing production-quality services with testing and monitoring.
• Ability to evaluate technical alternatives and make pragmatic architecture decisions.

Responsibilities

• Own components of an enterprise AI platform from evaluation and architecture through production deployment.
• Build frameworks and tooling supporting AI agents and agentic applications.
• Develop RAG and data-access patterns connecting internal information to AI applications.
• Build and operate MCP servers, gateways, plugins, and related integration services.
• Create evaluation and observability capabilities for testing and monitoring AI systems.
• Build secure authentication, authorization, and entitlement patterns around AI capabilities.
• Turn recurring application patterns into reusable platform components.
• Improve engineering standards, reliability, documentation, and developer workflows.

Skills

Software engineering

AI-enabled applications

RAG architectures

Security/auth patterns

Tools

AWS

DataDog

Identity management

Job description

A global investment-management organization is expanding an AI technology team responsible for building the shared infrastructure behind enterprise AI applications. The team is moving beyond isolated experimentation and creating a scalable platform that enables engineers and business teams to develop, deploy, evaluate, and operate AI agents in production.

This engineer will own meaningful pieces of that platform end-to-end. The work spans agent frameworks, RAG infrastructure, MCP services, developer tooling, enterprise data integration, observability, evaluation, authentication, and access control. This is a hands-on engineering position for someone who wants to build the infrastructure behind enterprise agentic AI rather than focus only on individual prototypes.

Responsibilities

• Own components of an enterprise AI platform from evaluation and architecture through production deployment.
• Build frameworks and tooling supporting AI agents and agentic applications.
• Develop RAG and data-access patterns connecting internal information to AI applications.
• Build and operate MCP servers, gateways, plugins, and related integration services.
• Create evaluation and observability capabilities for testing and monitoring AI systems.
• Build secure authentication, authorization, and entitlement patterns around AI capabilities.
• Turn recurring application patterns into reusable platform components.
• Improve engineering standards, reliability, documentation, and developer workflows.

Role Requirements

• Strong software-engineering background with significant hands-on development experience.
• Experience building AI-enabled applications, agentic workflows, or LLM infrastructure.
• Hands-on experience with RAG or enterprise-retrieval architectures.
• Understanding of how proprietary datasets are securely exposed to AI applications.
• Experience designing production-quality services with appropriate testing and monitoring.
• Ability to evaluate technical alternatives and make pragmatic architecture decisions.
• Strong communication and ability to collaborate across engineering teams.

Nice to Have

• AWS experience.
• Experience building internal developer platforms or engineering tooling.
• AI evaluation or observability experience.
• DataDog or similar tooling.
• Identity, authentication, or entitlement experience.
• Financial-services or investment-management technology experience.