27 days ago
Toronto, CanadaSenior
Responsibilities
- Build and own orchestration, retrieval, model-routing, tool-integration, reliability, prompt-management, caching, rate-limiting, and cost-attribution platform capabilities for AI agents.
- Design retrieval systems for large-scale legal document collections and define stable APIs and data contracts for product teams.
- Develop evaluation frameworks and quality gates measuring accuracy, grounding, citation quality, regressions, and overall system performance.
- Build observability, tracing, replay, monitoring, alerting, and incident-response capabilities for rapid troubleshooting and continuous improvement.
- Optimize latency, throughput, scalability, model selection, inference strategies, routing, and cost across interactive and batch workloads.
- Implement governance, auditability, human-in-the-loop controls, security, privacy, compliance, and data-residency protections for legal workflows.
- Set technical direction through design documents and architecture decision records, and mentor engineers through reviews, pairing, and technical guidance.
- Partner with Product Management, legal experts, and Review Operations to turn ambiguous problems into shippable scope.
Requirements
- Bachelor’s or master’s degree in computer science or a related technical field, or equivalent practical experience.
- 7+ years of experience building production software and owning systems end to end.
- Experience building production AI/LLM systems, including retrieval-augmented generation and agentic workflows.
- Strong Python skills and comfort working in a TypeScript codebase.
- Experience with distributed systems, asynchronous and event-driven architectures, and large batch data processing.
- Demonstrated production reliability ownership, including instrumentation, on-call, incident response, and data-driven performance work.
- Clear written communication and ability to explain technical decisions and trade-offs to technical and non-technical audiences.
- Preferred experience with LangGraph, LangChain, MCP, Langfuse, OpenTelemetry, vector databases, search infrastructure, information retrieval, hallucination detection, grounding verification, benchmarking, model fine-tuning, quantization, inference optimization, React, legal technology, eDiscovery, compliance, investigations, document review, multi-tenant SaaS, and PostgreSQL.
Benefits
- Enterprise-wide learning and mobility opportunities.
- Work flexibility recognized externally.
- May be eligible for an annual discretionary bonus.
- Applicants must be authorized to work in Canada and provide proof of right to work if required.
Tech Stack
Categories
