Principal AI Platform Engineer
- Toronto, ON, Canada
- Greater Toronto Area, Canada, Canada
Full-time
Applications open in a new tab.
Job details
- Job type
- Full-time
- Apply by
- Posting language
- English
- Posted
Original job description
Job Description:
Epiq supports some of the world's largest and most complex legal matters, where document collections range from thousands to millions of records. As a Principal AI Platform Engineer, you will design and build the platform our AI agents and accelerators run on, including orchestration, retrieval, evaluation, observability, and the inference path that keeps all of it fast and affordable at production scale.
This is a senior individual contributor role. You will write production code; own significant components end to end. You will set the technical direction that other engineers build on. You will also mentor engineers across our Toronto, US, and India teams through design reviews, code reviews, and pairing.
You will work across two product areas:
AI Agents. Conversational systems that enable legal professionals to ask complex questions and receive evidence-based answers grounded in case data.
AI Accelerators. AI-powered workflows that automate large-scale document review tasks including summarization, translation, transcription, language detection, and OCR.
Together, these solutions help legal teams reach defensible outcomes faster while reducing review costs and improving quality.
What You'll Do
Platform Engineering
- Build and own the platform capabilities that power AI agents, including orchestration, retrieval, model routing, tool integration, and reliability.
- Design retrieval systems across large-scale legal document collections.
- Develop shared platform services including prompt management, caching, rate limiting, and cost attribution.
- Define stable APIs and data contracts for product teams.
- Develop evaluation frameworks that measure accuracy, grounding, citation quality, and overall system performance.
- Build observability, tracing, and replay capabilities that enable rapid troubleshooting and continuous improvement.
- Establish quality gates and monitoring to identify regressions before they reach production.
- Optimize latency, throughput, and scalability across both interactive and batch workloads.
- Drive decisions around model selection, inference strategies, caching, and routing while managing cost as a first-class engineering metric.
- Build highly reliable systems through monitoring, alerting, incident response, and operational excellence practices.
- Implement governance, auditability, and human-in-the-loop controls required for legal and regulated workflows.
- Ensure compliance with security, privacy, and data residency requirements.
- Write the design docs and ADRs for consequential platform decisions, including the trade-offs you rejected.
- Raise the engineering bar through code review, pairing, and mentoring. Grow other engineers' judgment, not just their output.
- Partner with Product Management, legal domain experts, and Review Operations to turn ambiguous problems into shippable scope.
- Bachelor's or master’s degree in computer science or a related technical field, or equivalent practical experience.
- 7+ years building production software, with a track record of owning systems end to end.
- Experience building production AI/LLM systems, including retrieval-augmented generation and agentic workflows.
- Strong Python. Comfortable in a TypeScript codebase.
- Experience with distributed systems, asynchronous and event-driven architectures, and large batch data processing.
- Demonstrated ownership of production reliability: instrumentation, on-call, incident response, and performance work driven by data rather than intuition.
- Clear written communication. You can explain a design decision and its trade-offs to engineers and to non-engineers.
- Orchestration frameworks such as LangGraph, LangChain, MCP, etc.
- LLM observability and evaluation tooling such as Langfuse, OpenTelemetry, etc tracing.
- Vector databases, search infrastructure, and information retrieval fundamentals.
- Hallucination detection, grounding verification, and benchmarking methodology.
- Model fine-tuning, quantization, or inference optimization.
- React and modern frontend work for internal evaluation and debugging tools.
- Legal technology, eDiscovery, compliance, investigations, or document review.
- Multi-tenant SaaS platforms with strict data isolation requirements.
- Experience with PostgreSQL.
- The Compensation range for this role is $150,000 CAD up to $300,000 CAD annually and may be eligible for an annual discretionary bonus. This will be based on your background and skills alignment with the role.
Your specific salary will be determined based on several factors:
- Location-based market rate for the role
- Your abilities in relation to the job specification
- Performance during screening and interview
- Pay parity with the wider team in the considered location
Click Here To Learn About Epiq's Benefits.
Epiq Leadership Compass
Fosters Relationships & Collaboration
Builds trust and alignment through open communication, shared goals, and strong partnerships to drive collective success.
- Build trust-based partnerships
- Nurture long-term relationships
- Remove collaboration barriers
- Celebrate cross-team success
Inspires action and alignment through clear communication, purposeful influence, and a compelling vision.
- Use storytelling to build buy-in
- Align communication with organizational goals
- Guild alignment through strong engagement
Sets and reinforces performance standards that drive results, ensure accountability, and align with Epiq’s goals.
- Use data to identify improvement opportunities
- Make informed decisions
- Align team goals with boarder strategy
- Empower teams to manage their own goals
- Translate vision into clear priorities
- Prepare for disruptions with strong change management
Drives continuous improvement and operational excellence through smart processes, data insights, and quality execution.
- Improve workflows for team efficiency
- Use clear documentation and expectations
- Resolve issues quickly using data and feedback
More about this job
Responsibilities
Design, build, and own the production platform powering AI agents and document-review accelerators, including orchestration, retrieval, evaluation, observability, inference, and shared services. Set technical direction, improve system quality, performance, cost, reliability, and governance, and mentor engineers while partnering with product, legal, and operations teams.
Requirements
Requires a bachelor's or master's degree in computer science or a related field, or equivalent practical experience, and at least seven years building production software. Candidates need strong Python skills, TypeScript familiarity, production experience with AI/LLM systems and retrieval-augmented generation, distributed and event-driven systems experience, and demonstrated ownership of reliability and clear technical communication.
Skills
- Python
- TypeScript
- AI/LLM Systems
- Retrieval-Augmented Generation
- Agentic Workflows
- Distributed Systems
- Event-Driven Architecture
- Large-Scale Data Processing
- AI Orchestration
- Information Retrieval
- LLM Evaluation
- Observability
- Inference Optimization
- Production Reliability
- PostgreSQL
- Technical Mentoring
Visa sponsorship
Not detected in the job text
Categories
- Technology
- Software
- Engineering
- Legal
- Data & Analytics
Keywords
- Python
- TypeScript
- React
- LangGraph
- LangChain
- Model Context Protocol (MCP)
- Langfuse
- OpenTelemetry
- PostgreSQL
- Retrieval-Augmented Generation
- AI Agents
- LLM Orchestration
- Vector Databases
- Search Infrastructure
- Information Retrieval
- LLM Evaluation
- Grounding Verification
- Hallucination Detection
- Model Fine-Tuning
- Quantization
- Inference Optimization
- Distributed Systems
- Event-Driven Architecture
- Batch Data Processing
- Observability
- Tracing
- Multi-Tenant SaaS
- Data Residency
- eDiscovery
- Document Review