Principal AI Platform Engineer

Job summary

Design and build the production platform for AI agents and AI-powered document review workflows used in complex legal matters involving collections from thousands to millions of records. Own capabilities spanning orchestration, retrieval, evaluation, observability, inference, reliability, and governance, while optimizing performance and cost and setting technical direction. The role also includes mentoring engineers and supporting evidence-based answers and defensible legal outcomes.

Benefits

Qualifications

• At least 7 years of production software development experience, including end-to-end system ownership.
• Experience building production AI/LLM systems, including retrieval-augmented generation and agentic workflows.
• Strong Python skills and ability to work in TypeScript codebases.
• Experience with distributed systems, asynchronous and event-driven architectures, and large-scale batch data processing.
• Ownership of production reliability, including instrumentation, on-call, incident response, and data-driven performance work.
• Ability to explain technical decisions and trade-offs clearly to technical and nontechnical audiences.
• Bachelor's or master's degree in computer science or a related technical field, or equivalent practical experience.

Responsibilities

• Build and own platform capabilities for AI agents, including orchestration, retrieval, model routing, tool integration, and reliability.
• Design retrieval systems for large legal document collections.
• Develop shared services for prompt management, caching, rate limiting, and cost attribution.
• Define stable APIs and data contracts for product teams.
• Create evaluation frameworks for accuracy, grounding, citation quality, and system performance.
• Build observability, tracing, and replay capabilities for troubleshooting and continuous improvement.
• Establish quality gates and monitoring to detect production regressions.
• Optimize latency, throughput, scalability, model selection, inference strategies, caching, and routing across interactive and batch workloads.
• Implement monitoring, alerting, incident response, governance, auditability, and human-in-the-loop controls.
• Address security, privacy, and data residency requirements.
• Write design documents and architecture decision records, explaining trade-offs.
• Mentor engineers through design reviews, code reviews, and pairing.
• Partner with product management, legal domain experts, and review operations to define shippable scope.

Skills

Degrees

Languages

Industry

Relocation