Senior Data Scientist

LexisNexis

Senior Data Scientist building production generative AI, RAG, and agentic systems for LexisNexis legal information technology. Improving LLM drafting and retrieval through advanced search, evaluation, and reliable Python applications.

Posted 8/7/2026full-timeRaleigh • Florida, North Carolina, Virginia • 🇺🇸 United StatesSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates advanced Python proficiency in designing, implementing, and refactoring production applications while ensuring modularity, observability, and performance. Capable of managing the entire application lifecycle, from development through deployment and incident response, with a strong focus on testing and operational risk management.

Highest-signal resume keywords

Advanced Python ProficiencyAutomated Testing with PytestProduction ObservabilityCode Review and Risk IdentificationDistributed Application Design

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Python ProgrammingData StructuresAlgorithmsObject-Oriented DesignFunctional DesignType AnnotationsModular Application DevelopmentPerformance OptimizationFailure-Mode TestingProduction Readiness

Tools & Technologies

PytestRuffMypyProfiling ToolsPydantic

Industry Keywords

ObservabilityIncident ResponseSeparation of ConcernsDependency InjectionConfiguration ManagementGraceful DegradationToken ConsumptionModel Cost ControlStructured LoggingAlerting

Tech Stack

Tools & technologies

Python

About the role

Key responsibilities & impact

Architect modular agentic applications separating retrieval, prompt construction, model invocation, tool execution, state and history management, orchestration, validation, and response formatting
Refactor complex or legacy Python code for correctness, readability, modularity, extensibility, testability, and performance
Own production readiness for AI components, including validation, exception handling, timeouts, retries, fallback behavior, configuration, and credential security
Establish observability through structured logging, metrics, distributed tracing, alerting, and actionable error reporting
Design interfaces and data contracts between retrieval, orchestration, model, and downstream components
Write unit, integration, regression, and end-to-end tests, including failure-mode testing
Review Python and agentic application code and identify architectural and operational risks
Diagnose and optimize latency, memory usage, retrieval performance, token consumption, model cost, and scalability
Apply data structures, algorithms, and computational-complexity analysis
Participate in deployments, incident investigation, root-cause analysis, remediation, and reliability improvements

Requirements

What you’ll need

Advanced Python proficiency designing, implementing, debugging, testing, reviewing, and refactoring production applications
Strong command of Python fundamentals, data structures, algorithms, object-oriented and functional design, type annotations, and complexity analysis
Ability to transform prototype or experimental code into modular, maintainable, observable, production-ready systems
Strong understanding of separation of concerns, dependency injection, interface design, configuration management, and abstraction
Experience with automated unit, integration, regression, and end-to-end testing using tools such as pytest
Experience designing resilient distributed applications handling 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
Ability to conduct rigorous code reviews and identify correctness, maintainability, performance, security, testing, and operational risks
Experience owning applications across their lifecycle from design and experimentation through deployment, monitoring, incident response, and 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: Python quality tooling including pytest, ruff, mypy, profiling tools, and automated CI quality gates
Preferred: typed schemas and LLM input/output validation using tools such as Pydantic
Preferred: evaluation frameworks for agentic systems
Preferred: model fallbacks, tool-use controls, guardrails, human-in-the-loop workflows, and auditability
Preferred: production service support and incident response experience

Benefits

Comp & perks

Flexible working hours
Wellbeing initiatives
Shared parental leave
Study assistance
Sabbaticals
Country specific benefits
Accommodation or adjustment support during the hiring process