Lead/Senior Inference Engineer

Thomson Reuters•Frisco, TX
•$127,400 - $236,600

About The Position

Thomson Reuters Labs is the research and development division of Thomson Reuters, bringing together scientists, engineers, and domain experts to develop AI products for professional workflows. The team builds custom models using Thomson Reuters content and subject-matter expertise. This role will build and operate Mariner, Thomson Reuters’ custom inference platform, which serves production traffic for the Thomson model family and benchmark frontier models. The platform is expanding to additional product integrations and business lines and supports the company’s infrastructure sovereignty strategy. This is a hands-on engineering role focused on building the serving stack, optimizing inference cost and latency, and maintaining reliable production traffic as the platform scales to new integrations and international deployments. The successful candidate will be a founding engineer on a newly formed team, with autonomy and responsibility for shaping its technical strategy. The position reports to the Director, Model Inference Engineering and works closely with training and evaluation teams, research and product stakeholders, and engineering leadership. The posting is for proactive recruitment and may be used to fill current openings or future vacancies. The role may be eligible for an annual bonus based on enterprise and individual performance. The posting closes March 31, 2027.

Requirements

  • Hands-on infrastructure engineering experience with Kubernetes or a similar platform, including production system ownership.
  • Experience keeping model services available across multiple use cases, including peak load, scaling, disaster recovery, and operational excellence.
  • Direct experience with model-serving infrastructure and/or inference optimization for large models.
  • Large-scale distributed systems experience, including scaling and reliability under production load.
  • Ability to debug distributed systems and production incidents under real traffic.
  • Track record of shipping software end to end: designing, building, and operating production systems.
  • Ability to champion and enforce engineering best practices while responding to changing product requirements.
  • Ability to operate autonomously as an early lead engineer and mentor and grow team members.

Nice To Haves

  • Experience with LLM-serving stacks such as vLLM, TensorRT-LLM, Triton, or SGLang, or similar.
  • Exposure to GPU-cluster capacity planning or multi-region/multi-cloud deployment.
  • Exposure to a regulated or compliance-heavy production environment, such as ISO 27001 or SOC 2.
  • Familiarity with systems development languages such as Rust or Go.
  • Comfort with systems-level optimization, including rate-limiting and routing improvements and identifying bottlenecks across networking, hardware, and lower-level software.

Responsibilities

  • Build and operate the model-serving infrastructure that handles Thomson Reuters production traffic.
  • Implement and tune inference-optimization techniques, such as batching, caching, and quantization, to reduce cost and latency without sacrificing quality.
  • Improve Mariner’s observability as call volume and the deployment surface grow.
  • Implement controls and evidence supporting the ISO 27001 compliance path.
  • Build cost-tracking and attribution capabilities used by Finance.
  • Develop GPU-capacity contingency plans to prevent downtime or costly parallel running when capacity changes.
  • Document cost, latency, and reliability tradeoffs and communicate them to the Director and partner teams.
  • Work with training and evaluation pods to deploy new model releases on the serving stack.
  • Help establish team practices and tooling, including on-call, incident reviews, and onboarding.
  • Collaborate with research and product stakeholders and engineering leadership to keep the serving stack aligned with new model releases.
  • Operate autonomously as an early lead engineer and mentor and grow team members as the team scales.

Benefits

  • Flexible work arrangements, including work from anywhere for up to 8 weeks per year.
  • Flexible vacation and paid time off, including sick and safe time 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 in the United States.
  • Tuition reimbursement.
  • Employee incentive programs; the role may also be eligible for an annual bonus based on enterprise and individual performance.
  • Health, dental, vision, disability, and life insurance programs in the United States.
  • Paid parental leave and sabbatical leave.
  • Fitness reimbursement.
  • Flexible Spending and Health Savings Accounts.
  • Commuter benefits.
  • Adoption and surrogacy assistance.
  • Employee Stock Purchase Plan.
  • Two paid volunteer days off annually and opportunities for pro-bono consulting and ESG initiatives.
  • Resources for mental, physical, and financial wellbeing.
  • Optional hospital, accident and sickness insurance; optional life and AD&D insurance; and group legal and identity theft protection, paid 100% by the employee.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service