Job Description

Accountabilities:

• Design, build, and own platform capabilities supporting AI agents, including orchestration, retrieval, model routing, tool integration, and reliability.
• Architect retrieval systems capable of operating across large-scale document collections and complex information environments.
• Develop shared platform services for prompt management, caching, rate limiting, cost attribution, and other reusable AI capabilities.
• Define stable APIs, interfaces, and data contracts that enable product teams to build consistently on the platform.
• Build evaluation frameworks measuring accuracy, grounding, citation quality, and overall AI system performance.
• Develop observability, tracing, and replay capabilities to support troubleshooting, performance analysis, and continuous improvement.
• Establish quality gates and production monitoring to detect regressions before they impact users.
• Optimize latency, throughput, scalability, and cost across interactive and batch AI workloads.
• Make informed decisions regarding model selection, inference strategies, caching, routing, and other performance-critical areas.
• Build reliable production systems through monitoring, alerting, incident response, and operational excellence practices.
• Implement governance, auditability, and human-in-the-loop controls appropriate for legal and regulated workflows.
• Ensure solutions meet applicable security, privacy, and data residency requirements.
• Lead consequential technical decisions through architecture documentation, design documents, and Architecture Decision Records (ADRs).
• Raise engineering standards through code reviews, technical pairing, mentoring, and knowledge sharing.
• Partner with product managers, legal domain specialists, and operations teams to translate ambiguous business challenges into well-defined, shippable solutions.

Requirements

• Bachelor’s or master’s degree in Computer Science, Engineering, or a related technical discipline, or equivalent practical experience.
• 7+ years of professional experience building production software, with demonstrated ownership of systems and components end to end.
• Proven experience developing production AI/LLM systems, particularly retrieval-augmented generation (RAG) and agentic workflows.
• Strong proficiency in Python and the ability to work comfortably within TypeScript codebases.
• Solid understanding of distributed systems, asynchronous and event-driven architectures, and large-scale batch data processing.
• Demonstrated experience owning production reliability, including instrumentation, monitoring, on-call practices, incident response, and data-driven performance optimization.
• Strong architectural and systems-thinking capabilities, with the ability to evaluate technical trade-offs and make sound engineering decisions.
• Excellent written and verbal communication skills, with the ability to explain complex technical decisions to both engineering and non-technical stakeholders.
• Ability to work independently, take ownership of significant technical areas, and influence engineering direction without direct management responsibility.
• Experience mentoring engineers and raising technical standards through design reviews, code reviews, and collaborative problem-solving.

Preferred qualifications:

• Experience with AI orchestration frameworks such as LangGraph, LangChain, or MCP.
• Experience with LLM observability and evaluation tooling, including Langfuse or OpenTelemetry-based tracing.
• Knowledge of vector databases, search infrastructure, and information retrieval fundamentals.
• Experience with hallucination detection, grounding verification, benchmarking, and AI quality evaluation methodologies.
• Experience with model fine-tuning, quantization, or inference optimization.
• React and modern frontend development experience, particularly for internal evaluation and debugging tools.
• Background in legal technology, eDiscovery, compliance, investigations, or document review.
• Experience building multi-tenant SaaS platforms with strict data isolation requirements.
• Experience working with PostgreSQL.

Benefits

• Competitive salary range of CAD $126,000–$175,000 per year, depending on location, experience, skills, and overall alignment with the role.
• Eligibility for an annual discretionary bonus.
• Hybrid work model with part-time office presence in Toronto, Ontario
• Opportunity to work on high-impact AI platforms supporting complex, global workflows.
• Significant technical ownership and the opportunity to influence architecture and engineering standards.
• Collaboration with international engineering teams across Canada, the United States, and India.
• Mentorship and professional development opportunities.
• Opportunity to work with modern AI, cloud, distributed systems, and observability technologies.
• Inclusive and collaborative work environment focused on teamwork and continuous improvement.
• Reasonable accommodations available throughout the hiring process for candidates who require them.
• Candidates must be authorized to work in Canada and may be required to provide proof of work authorization.