Sr Data Scientist II

LexisNexis; Toronto; On-site; CAD 108,000 - 158,000; Full time

Benefits offered by this job

Shared parental leave

Study assistance

Sabbaticals

Job summary

LexisNexis Legal & Professional in Toronto is seeking a Senior Data Scientist II with deep expertise in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI systems. This role focuses on improving LLM-powered drafting and retrieval solutions through advanced search, embeddings, reranking, evaluation, and production-grade ML components.

You will independently design, refactor, test, review, deploy, and support clean Python applications, ensuring logging, monitoring, and secure

Qualifications

• Advanced Python proficiency demonstrated through production apps.
• Strong command of Python fundamentals, data structures, and algorithms.
• Experience transforming prototypes into production-ready systems.
• Knowledge of software design, DI, interfaces, and configuration mgmt.
• Experience with pytest and mocking external services.
• Designing resilient distributed apps with timeouts, retries and graceful degradation.
• Production observability: logs, metrics, tracing, alerts.
• Ability to review code for correctness, performance, and security.

Responsibilities

• Architect modular agentic applications for retrieval, prompt construction, model invocation, and orchestration.
• Refactor complex Python code for correctness, readability, and performance.
• Own production readiness including input validation, error handling, and credentials security.
• Establish observability for LLM and retrieval workflows with logging and metrics.
• Design interfaces and data contracts across components.
• Write unit, integration, regression, and end-to-end tests including failure modes.
• Review code for risks and provide actionable feedback to production standards.
• Diagnose and optimize latency, memory usage, and token costs.
• Participate in deployments, incident response, and reliability improvements.

Skills

Advanced Python

Python fundamentals

Testing with pytest

Distributed systems

Observability

Code reviews

Ownership

LLM/AI concepts

Tools

OpenSearch

Solr

Job description

About our Team

LexisNexis Legal & Professional, which serves customers in more than 150 countries with 11,800 employees worldwide, is part of RELX (http://www.relx.com), a global provider of information-based analytics and decision tools for professional and business customers. Our company has been a long-time leader in deploying AI and advanced technologies to the legal market to improve productivity and transform the overall business and practice of law, deploying ethical and powerful generative AI solutions with a flexible, multi-model approach that prioritizes using the best model from today’s top model creators for each individual legal use case. The company employs over 2,000 technologists, data scientists, and experts to develop, test, and validate solutions in line with RELX Responsible AI Principles (https://stories.relx.com/responsible-ai-principles/index.html).

About the Role

We are looking for a Senior Data Scientist II with deep expertise in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI systems, combined with strong software-engineering fundamentals and demonstrated ownership of production applications. This role will focus on improving LLM-powered drafting and retrieval solutions through advanced search, embeddings, reranking, evaluation, and production-grade ML components.

The successful candidate must be able to independently design, refactor, test, review, deploy, and support clean, reliable Python applications. This includes separating agent responsibilities, designing for failure, applying sound algorithmic reasoning, and establishing appropriate logging, monitoring, testing, and operational controls.

The ideal candidate has advanced Python proficiency, experience with OpenSearch or Solr, success working in monorepo environments, and a strong record of cross-functional delivery.

Key Responsibilities

• Architect modular agentic applications with clear separation among retrieval, prompt construction, model invocation, tool execution, state and history management, orchestration, validation, and response formatting.
• Independently refactor complex or legacy Python code to improve correctness, readability, modularity, extensibility, testability, and runtime performance.
• Own production readiness for AI components, including input validation, exception handling, timeout management, retries with backoff, fallback behavior, configuration management, and secure handling of credentials.
• Establish observability for LLM and retrieval workflows through structured logging, metrics, distributed tracing, alerting, and actionable error reporting.
• Design clear interfaces and data contracts between retrieval, orchestration, model, and downstream application components.
• Write comprehensive unit, integration, regression, and end-to-end tests, including tests for failure modes, malformed model responses, empty retrieval results, and unavailable dependencies.
• Review Python and agentic application code, identify architectural and operational risks, and provide actionable feedback aligned with production engineering standards.
• Diagnose and optimize latency, memory usage, retrieval performance, token consumption, model cost, and application scalability.
• Apply appropriate data structures, algorithms, and computational-complexity analysis when designing and optimizing solutions.
• Participate in production deployments, incident investigation, root-cause analysis, remediation, and continuous reliability improvements.

Required Qualifications

• Advanced Python proficiency demonstrated through independently designing, implementing, debugging, testing, reviewing, and refactoring production applications.
• Strong command of Python fundamentals, standard data structures, common algorithms, object-oriented and functional design principles, type annotations, and time and space complexity analysis.
• Demonstrated ability to transform prototype or experimental code into modular, maintainable, observable, and production‑ready systems.
• Strong understanding of software design principles, including separation of concerns, dependency injection, interface design, configuration management, and effective abstraction.
• Experience implementing automated unit, integration, regression, and end‑to‑end testing using tools such as pytest, including appropriate mocking of external services.
• Experience designing resilient distributed applications that account for timeouts, retries, rate limits, partial failures, malformed responses, idempotency, and graceful degradation.
• Experience with production observability, including structured logging, metrics, tracing, alerting, and incident troubleshooting.
• Demonstrated ability to conduct rigorous code reviews and identify correctness, maintainability, performance, security, testing, and operational risks.
• Experience taking technical ownership of applications across their lifecycle, from design and experimentation through deployment, monitoring, incident response, and ongoing improvement.
• Strong understanding of production LLM concerns, including structured output validation, context management, model and tool failures, prompt versioning, token and cost controls, security, and evaluation.

Preferred Qualifications

• Experience with Python quality tooling such as pytest, ruff, mypy, profiling tools, and automated CI quality gates.
• Experience defining typed schemas and validating LLM inputs and outputs using tools such as Pydantic.
• Experience building evaluation frameworks for agentic systems, including task‑completion, retrieval‑quality, groundedness, hallucination, latency, reliability, and cost metrics.
• Experience implementing model fallbacks, tool‑use controls, guardrails, human‑in‑the‑loop workflows, and auditability for AI applications.
• Experience supporting production services and participating in incident response, root‑cause analysis, and post‑incident remediation.

The successful candidate will:

• Demonstrate senior‑level Python proficiency and sound computer‑science fundamentals.
• Treat correctness, maintainability, testing, resilience, security, and observability as core design requirements.
• Recognize architectural issues and improve code beyond simply making it functional.
• Independently review and refactor complex agentic application code.
• Make clear engineering tradeoffs involving quality, latency, scalability, reliability, and cost.
• Take end‑to‑end ownership from experimentation through production deployment and operational support.
• Communicate technical decisions and code‑review feedback clearly and constructively.
• Combine strong LLM and retrieval expertise with disciplined software‑engineering practices.

Work in a Way That Works for You

We promote a healthy work/life balance across the organisation. We offer an appealing working prospect for our people. With numerous wellbeing initiatives, shared parental leave, study assistance and sabbaticals, we will help you meet your immediate responsibilities and your long‑term goals.

Working Pattern

Working flexible hours - flexing the times when you work in the day to help you fit everything in and work when you are the most productive.

About the Business

LexisNexis Legal & Professional® provides legal, regulatory, and business information and analytics that help customers increase their productivity, improve decision‑making, achieve better outcomes, and advance the rule of law around the world. As a digital pioneer, the company was the first to bring legal and business information online with its Lexis® and Nexis® services. #AIFluent

Primary Location Base Pay Range: Canada - Toronto (Yonge St) $108,100 - $158,100 (CAD). This job is eligible for an annual incentive bonus.This posting is not for an immediate existing vacancy but for a future opportunity.

USA Job Seekers:

EEO Know Your Rights.

We are an equal opportunity employer: qualified applicants are considered for and treated during employment without regard to race, color, creed, religion, sex, national origin, citizenship status, disability status, protected veteran status, age, marital status, sexual orientation, gender identity, genetic information, or any other characteristic protected by law.

Please read our Candidate Privacy Policy.