Description
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 state-of-the-art AI products.
You will work hands-on building and operating Mariner, Thomson Reuters' custom inference platform, serving every production call to the Thomson model family.
Key Responsibilities
- Build and operate the model-serving infrastructure that runs Thomson's production traffic.
- Implement and tune inference-optimization techniques to reduce cost and latency without sacrificing quality.
- Improve Mariner's observability as call volume and the deployment surface grow.
- Build out Thomson's production footing, implementing controls and evidence for ISO 27001 compliance.
- Make and document cost vs. latency vs. reliability tradeoffs.
- Work directly with the training and evaluation pods to get new model releases live on the serving stack.
- Help stand up the team's own practices and tooling.
Required Qualifications
- Hands-on infrastructure engineering experience with Kubernetes or similar.
- Experience keeping model services up across multiple use cases.
- Direct experience with model-serving infrastructure and/or inference optimization for large models.
- Large-scale distributed systems experience.
- Comfort debugging distributed systems and production incidents.
- A track record of shipping software end to end.
Preferred Qualifications
- Experience with common LLM-serving stacks.
- Exposure to GPU-cluster capacity planning or multi-region/multi-cloud deployment.
- Familiarity with systems development languages.
What's in it For You?
- Hybrid Work Model
- Flexibility & Work-Life Balance
- Career Development and Growth
- Industry Competitive Benefits
- Culture
- Social Impact
For more fresh new jobs, check out yubhub.co.