AI Platform & Systems Integration Engineer — New York, NY

AI Platform & Systems Integration Engineer

Location: New York, NY

Compensation: $170-200K + bonus

Responsibilities:

• Own the end-to-end design of ingestion, transformation, and indexing pipelines connecting document management systems (DMS) and enterprise repositories to vector databases and LLM backends.

• Design and maintain production-grade REST and event-driven APIs, tool-calling interfaces (including Model Context Protocol / MCP), and middleware that connect autonomous agents with core business systems.

• Engineer robust access-control propagation to ensure ethical walls, matter restrictions, and granular user permissions remain uncompromised across indexing pipelines, vector stores, and AI responses.

• Establish real-time change-data-capture (CDC) and synchronization routines that reflect document edits, access revocations, retention policies, and deletions across downstream AI indices instantly.

• Collaborate with AI evaluation teams to translate ingestion failure modes, context drift, and retrieval bottlenecks into automated test suites, benchmarking frameworks, and regression controls.

• Lead cross-functional delivery across internal engineers and external vendor teams. Run code reviews, define architecture standards, mentor junior talent, and articulate trade-offs clearly to legal, security, and executive partners.

• Triage complex production issues spanning API gateways, asynchronous message buses, retrieval pipelines, and AI orchestrators, balancing latency, cost, and reliability.

Qualifications:

Required

• 5+ years of hands-on experience in data engineering, backend integration, or distributed platform engineering, with a proven track record of taking complex data infrastructure into production.

• Technical leadership experience, having guided technical roadmaps, run design reviews, and mentored engineering teams.

• Mastery of building and securing RESTful and event-driven architectures (Kafka, message queues, webhooks), API gateways, OAuth/OIDC, schema versioning, idempotency, rate limiting, and observability.

• Strong working knowledge of LLM failure modes, unstructured data extraction, vector databases, hybrid search (keyword + dense embeddings), re-ranking strategies, and RAG architectures.

• Experience implementing complex authorization models, multi-tenant isolation, or information barriers in regulated or high-compliance environments.

• Proficiency in Python, Java, or C#, alongside standard engineering workflows (CI/CD, Docker, Git, automated testing frameworks).

• Hands-on familiarity leveraging modern AI developer tools (coding agents, LLM-assisted workflows) responsibly, with strong instincts for context management, security validation, and code scrutiny.

Preferred

• Background in legal tech or highly regulated professional services (e.g., finance, healthcare, consulting).

• Hands-on familiarity with enterprise DMS platforms (such as iManage, NetDocuments), knowledge graphs, legal ontologies, or entity resolution.

• Experience implementing governed agentic tool interfaces (such as Anthropic’s Model Context Protocol or function-calling tool standards).