AI Engineer - Full Stack

PRI Technology; New York (NY); On-site; USD 140,000 - 200,000; Full time

Job summary

PRI Technology in New York seeks an AI Engineer to lead the design, build, and end-to-end delivery of business-facing AI applications and automation across the Firm. You will collaborate with front office Investment Professionals to translate workflows into technical specifications and own timely delivery within the Firm’s ecosystem.

This hands-on role combines stakeholder engagement, software development, testing, deployment, and support.

Qualifications

• Designing, building, and troubleshooting APIs and connectors.
• Strong SQL and relational DB knowledge.
• Proficient in Git, testing, debugging, and deployment practices.
• Experience with generative AI architecture and LLM integrations.

Responsibilities

• Partner with Business to translate workflows into user stories and specs.
• Lead full-stack development of applications, dashboards, and tools.
• Own design, build, test, and maintenance of API integrations and MCP connectors.
• Develop configurable templates and reusable components for multi-deal use.
• Apply best practices: version control, code reviews, automated testing, secure credentials, logging.

Skills

API design & integration

Full-stack development

SQL & Relational databases

Git & testing & deployment

Generative AI & LLM integration

Stakeholder communication

Education

Bachelor’s degree in Computer Science or related field

Tools

MCP connectors

Azure cloud

CI/CD tools

Job description

Top tier financial investment firm seeks an AI Engineer who will lead the design, build, and end-to-end delivery of business-facing AI applications and automation across the Firm. As a member of the AI team within Business Technology, the AI Engineer will work directly with front office Investment Professionals to understand transaction workflows, translate business needs into technical specifications, and own delivery of practical solutions within the Firm’s ecosystem, anticipating issues and managing priorities, resources, and timelines.

This is a hands-on, full-stack engineering role combining stakeholder engagement, requirements analysis, software development, testing, deployment, and support. The AI Engineer will also contribute to the Firm’s internal AI platform by building and maintaining reusable API integrations, Model Context Protocol (MCP) connectors, and workflow components that securely connect AI applications and agents to approved enterprise systems and data.

The AI Engineer will lead day-to-day delivery with a high degree of independence, provide technical guidance and mentoring to junior colleagues, and coordinate with Businesses, Data Science, IT, Information Security, Compliance, and external vendors.

Responsibilities

• Partner with Business to lead requirements gathering and documentation; translate workflows into user stories, technical specifications, and acceptance criteria. Evaluate existing tools before recommending a new build.
• Lead the design and development of full-stack applications, dashboards, and workflow tools, connecting user interfaces, APIs, databases, and approved AI services to support information synthesis and banker productivity.
• Own the design, build, testing, and maintenance of secure, reusable API integrations and MCP connectors between the Firm’s AI platform and approved enterprise systems, data sources, and third‑party services.
• Lead the development and maintenance of reviewed, configurable templates and reusable components so solutions can be adapted across transactions rather than rebuilt for each deal. Guide AI workflow orchestration and contribute to technical planning.
• Apply and reinforce engineering best practices, including version control, peer code review, automated testing, secure credential management, logging, and technical documentation. Evaluate AI output quality, reliability, latency, and cost.
• Lead user acceptance testing, user training, and feedback. Work with IT and engineering on approved deployment, monitoring, support handover, and retirement of temporary deal tools.
• Partner with Information Security and Compliance to identify and review material changes to solutions or enhancements that warrant additional assessment.

Qualifications

• Demonstrated expertise designing, building, consuming, and troubleshooting APIs and connectors, with familiarity with Model Context Protocol (MCP) desirable.
• Strong working knowledge of SQL and relational databases
• Proficiency in Git, testing, debugging, and deployment practices, with the ability to write clear, maintainable, reviewable code.
• Working knowledge of generative AI architecture and demonstrated experience with large language model integration, including output validation and the limitations of AI-generated results and code.
• Ability to translate complex business needs into workable technical solutions, exercise sound technical judgment, and explain trade-offs and business objectives clearly to technical and non-technical stakeholders.
• Strong analytical thinking, organization, documentation, attention to detail, and customer service orientation. Sound judgment when handling confidential information and escalating risks.
• Intellectual curiosity, adaptability, and the ability to lead projects from start to finish with a high degree of independence, guide junior colleagues, and recognize when to involve senior colleagues on architecture, security, and production readiness.

Plusses

• Experience with AI-enabled applications, retrieval-augmented generation, agent workflows, or model evaluation.
• Experience with cloud platforms such as Azure, containers, CI/CD, authentication, role-based access controls, and application monitoring.
• Experience working in an Agile environment, using tools such as Jira, and conducting stakeholder demos, user acceptance testing, or user training.

Education & Experience

• Bachelor’s degree in Computer Science, Software Engineering, or a related technical field
• Demonstrated professional experience delivering full-stack applications and integrations, with ownership of projects or workstreams from requirements through deployment and support.