AI Data & Integration Engineer

Freshfields•Raleigh, NC

About The Position

The AI Data & Integration Engineer leads the design and delivery of secure, reliable, and scalable data foundations and integrations that support AI applications across a global law firm. The role enables AI assistants, enterprise search, and agent workflows to access legal and business information with appropriate context, permissions, quality, and traceability. The engineer owns the architecture and technical design of data pipelines and API integrations connecting enterprise systems, cloud services, AI platforms, and agent tools. They establish reusable approaches for data ingestion, transformation, indexing, access, synchronization, and governed data products. The position also ensures that permissions, information barriers, client restrictions, document changes, retention decisions, and deletions are correctly reflected across downstream systems. Working with AI evaluation engineers and other teams, the role translates data, retrieval, and integration failure modes into measurable tests, regression suites, and production controls. It diagnoses production issues across source systems, APIs, pipelines, indexes, and AI applications, while balancing quality, security, performance, cost, and maintainability. The role leads technical delivery across internal teams and external partners, reviews architecture and code, mentors engineers, manages dependencies, and translates business, legal, and governance requirements into delivery plans.

Requirements

Strong experience managing or leading teams that design, deliver, and operate production application or data platforms and integrations.
Deep practical experience designing and integrating RESTful and event-driven APIs, including authentication and authorization, API gateways, schema and contract management, versioning, retries, rate limits, error handling, observability, and secure integration with enterprise and third-party systems.
Strong conceptual understanding of large language models, including capabilities, limitations, and common failure modes, and how data quality, context, retrieval, permissions, and integration design affect AI application performance and evaluation outcomes.
Knowledge of unstructured document processing and retrieval-augmented generation, including search indexes, embeddings, hybrid retrieval, reranking, and retrieval evaluation.
Demonstrated ability to design secure data services and implement granular access controls and information barriers.
Proficiency using coding agents to accelerate design, development, testing, and troubleshooting, with sound judgment about human review and best practices for prompting, context management, validation, security, and responsible use of generated code.
Experience developing software in languages such as Python, Java, or C#, and applying sound software engineering practices to reusable libraries, services, and integration components.
Experience with SDLC methodologies and associated development, automated testing, and CI/CD tools such as Git, Jira, and Jenkins.
Demonstrated ability to learn continuously in a rapidly evolving AI, data, and integration landscape, critically assess new tools and techniques, and apply relevant advances pragmatically.
Experience making architectural decisions, leading complex technical delivery, reviewing designs and code, and developing other engineers.
Ability to explain technical choices clearly to business, legal, security, and governance stakeholders.
At least five years of experience in data engineering, integration engineering, or a closely related discipline.

Nice To Haves

Legal or professional services experience.
Familiarity with iManage or comparable document management systems, entity resolution, legal taxonomies, knowledge graphs, and governed agent integrations such as MCP.

Responsibilities

Own the architecture and technical design of data pipelines connecting document management, knowledge, client, matter, and business systems to AI platforms.
Establish reusable patterns for ingestion, transformation, indexing, access, and synchronization.
Lead the design, implementation, and operation of secure API integrations between enterprise systems, cloud services, AI platforms, and agent tools.
Define standards for authentication, authorization, versioning, error handling, observability, rate limiting, and resilient data exchange.
Ensure source permissions, information barriers, and client restrictions remain effective during processing, integration, and retrieval.
Design mechanisms to propagate document updates, permission changes, retention decisions, and deletions to downstream stores, indexes, and applications.
Develop consistent data models linking clients, matters, people, and documents.
Provide governed data products, APIs, and tool interfaces that enable AI applications and agents to retrieve and act on information safely.
Partner with AI evaluation engineers to turn data, retrieval, and integration failure modes into measurable tests, regression suites, and production controls; use results to improve data and API design.
Diagnose complex production issues across source systems, APIs, data pipelines, indexes, and consuming AI applications, balancing quality, security, performance, cost, and maintainability.
Lead technical delivery across internal teams and external partners.
Review architecture and code, mentor engineers, manage technical dependencies, and translate business, legal, and governance requirements into practical delivery plans.
Continuously assess new tools and techniques and apply relevant advances pragmatically to improve products, engineering practices, and risk controls.