Director, Model Inference Engineering

Thomson Reuters•Eagan, MN
•Hybrid

About The Position

Thomson Reuters Labs is the global research and development division of Thomson Reuters, bringing together scientists, engineers, and domain experts to explore emerging technologies and develop AI products. It builds custom models for professional workflows, including the Thomson LLM model family, trained on authoritative Thomson Reuters content with subject-matter-expert input. Mariner is Thomson Reuters’ custom inference platform and serves production calls to the Thomson model family. The Director, Model Inference Engineering leads and grows the team responsible for Mariner. The role works with senior technical leadership and cross-functional partners to ensure the platform is production-ready and supports cost tracking, compliance, and capacity planning as it scales. The director partners with research and product stakeholders so the serving stack keeps pace with model releases and product expansion. This posting is for proactive recruitment and may be used to fill current or future vacancies.

Requirements

  • Experience leading or managing inference infrastructure for large models in production at meaningful traffic and scale, rather than only in research or prototype settings.
  • Demonstrated results delivered by teams the candidate has led, with the technical fluency to hire, coach, and advocate for the work.
  • End-to-end ownership of a cost-attribution or compliance program, including control design, evidence collection, and an external audit such as ISO 27001, SOC 2, or comparable.
  • Experience with production systems running on Kubernetes or a similar platform.
  • Track record building and leading a focused engineering team; growing a team from a small group of engineers is ideal.
  • Experience managing resource constraints, including GPU capacity, region availability, and cost.
  • Experience supporting external-facing or customer-facing deployments, not only internal research infrastructure.
  • Operational excellence in engineering teams and systems.

Nice To Haves

  • Experience with LLM-serving stacks such as vLLM, TensorRT-LLM, Triton, SGLang, or similar.
  • Experience working with research and product stakeholders to define the engineering roadmap for a production system.
  • Exposure to GPU-cluster capacity planning or multi-region or multi-cloud deployment.
  • Familiarity with systems-development languages such as Rust or Go.
  • Exposure to a regulated or compliance-heavy production environment.

Responsibilities

  • Grow and lead the inference-engineering team, including setting the hiring bar, conducting performance and growth conversations, retaining team members, and establishing sustainable operating practices for on-call, incident reviews, and onboarding.
  • Own delivery of Mariner’s engineering roadmap, planning and resourcing work against objectives and key results with technical leadership, engineers, and researchers.
  • Drive product integrations and international deployment while balancing cost and latency targets.
  • Lead the production platform’s ISO 27001 compliance path.
  • Deliver cost tracking and attribution for Finance.
  • Plan for GPU capacity contingencies so changes in capacity do not cause downtime or costly parallel running.
  • Represent inference-engineering tradeoffs involving cost, latency, and reliability to senior leadership and cross-functional partners.
  • Ensure token-economics benchmarks are produced and published to demonstrate Thomson’s cost advantage over closed-model APIs when supported by the data.

Benefits

  • Flexible hybrid work environment for office-based roles.
  • Flexible work arrangements, including work from anywhere for up to 8 weeks per year.
  • Flexible vacation and paid time off, including sick and safe paid time off and paid holidays.
  • Two company-wide Mental Health Days off annually.
  • Access to the Headspace app and Employee Assistance Program.
  • Retirement savings plan with company match.
  • Tuition reimbursement.
  • Employee incentive programs and possible annual bonus based on enterprise and individual performance.
  • Resources for mental, physical, and financial wellbeing.
  • Two paid volunteer days off annually and opportunities for pro-bono consulting and ESG initiatives.
  • Health, dental, vision, disability, and life insurance programs.
  • Parental leave and sabbatical leave.
  • Flexible Spending and Health Savings Accounts.
  • Fitness reimbursement.
  • Optional hospital, accident and sickness insurance, paid by the employee.
  • Optional life and AD&D insurance, paid by the employee.
  • Group legal and identity theft protection benefit, paid by the employee.
  • Access to a 529 Plan.
  • Commuter benefits.
  • Adoption and surrogacy assistance.
  • Employee Stock Purchase Plan.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service