Beskrivningen av det här företaget är ännu inte tillgänglig på det här språket.
Director, Model Inference Engineering
Du bygger och driver Mariner, inferensplattformen som betjänar Thomson Reuters modeller i produktion. Du optimerar kostnader, svarstid och tillförlitlighet samt utvecklar teamets observerbarhet och arbetssätt. Tjänsten är placerad i Zug och har en hybrid arbetsmiljö.
3× större chans till intervju med ett kallt mejl
Visa originalannonsenFakta om Thomson Reuters
- Officiell domän
- thomsonreuters.com
- Lediga jobb
- 9
Om annonsen
Den fullständiga beskrivningen som publicerats av Thomson Reuters.
Job Description Thomson Reuters Labs is the global research and development division of Thomson Reuters. We bring together scientists, engineers, and domain experts to explore emerging technologies and develop state-of-the-art AI products, bridging frontier science with practical application. Labs builds and ships custom models for professional workflows requiring fiduciary-grade AI. The Thomson LLM model family was developed by training leading open-weight models on decades of authoritative Thomson Reuters content, with thousands of hours of subject-matter-expert input.
Owning the model layer is how we earn trust in the most regulated, highest-stakes professional workflows. You'll work hands-on building and operating Mariner, Thomson Reuters' custom inference platform. Mariner serves every production call to the Thomson model family, plus the frontier models we benchmark against, and is scaling to new product integrations and business lines. It is a key pillar of our infrastructure sovereignty strategy.
This is a hands-on engineering seat, not a research role: you'll be the one actually building the serving stack, tuning inference for cost and latency, and keeping production traffic reliable as Mariner scales to new product integrations and international deployments. You'll join as one of the founding engineers on a newly built team, reporting to the Director, Model Inference Engineering, with real autonomy and the expectation to shape the team's technical strategy from the start.
For more on the latest model release, see the Thomson 1.0 Technical Report on Hugging Face: https://huggingface.co/spaces/tri-fair-lab/publications/blob/main/Thomson_1_0_Technical_Report.pdf Key Responsibilities
- Build and operate the model-serving infrastructure that runs Thomson's production traffic.
- Implement and tune inference-optimization techniques (batching, caching, quantization, or comparable) 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: implement the controls and evidence for the ISO 27001 compliance path, the cost-tracking and attribution Finance relies on, and GPU-capacity contingency plans so a capacity change doesn't force downtime or costly parallel running.
- Make and document cost vs. latency vs. reliability tradeoffs, and bring them to the Director and partner teams.
- 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 (on-call, incident reviews, onboarding) as an early member, rather than inheriting a fixed system.
- Collaborate with research and product stakeholders and engineering leadership so the serving stack keeps pace with new model releases. Required Qualifications
- Hands-on infrastructure engineering experience with Kubernetes or similar, comfortable owning a system in production rather than only prototyping one.
- Experience keeping model services up across multiple use cases: peak load, scaling, disaster recovery, and operational excellence.
- Direct experience with model-serving infrastructure and/or inference optimization for large models, at whatever scale you've worked at so far.
- Large-scale distributed systems experience, including scaling and reliability under production load.
- Comfort debugging distributed systems and production incidents under real traffic.
- A track record of shipping software end to end: design, build, and operate production systems.
- Champion and enforce engineering best practices while working with dynamic product requirements.
- Ability to operate autonomously as an early lead engineer, and to mentor and grow other team members as the team scales. Preferred Qualifications
- Experience with common LLM-serving stacks (vLLM, TensorRT-LLM, Triton, SGLang, or similar).
- Exposure to GPU-cluster capacity planning or multi-region/multi-cloud deployment.
- Exposure to a regulated or compliance-heavy production environment (ISO 27001, SOC 2, or comparable).
- Familiarity with systems development languages (Rust, Go, etc.).
- Comfort with systems-level optimization: improvements to rate-limiting and routing approaches, and identifying bottlenecks across networking, hardware, and lower-level software. Even if you don't have all of the above requirements, we encourage you to apply to explore a mutual fit! #LI-FP3 What’s in it For You?
- Hybrid
Work Model: We’ve adopted a flexible hybrid working environment for our office-based roles while delivering a seamless experience that is digitally and physically connected. - Flexibility & Work-Life Balance: Flex My Way is a set of supportive workplace policies designed to help manage personal and professional responsibilities, whether caring for family, giving back to the community, or finding time to refresh and reset.
This builds upon our flexible work arrangements, including work from anywhere for up to 8 weeks per year, empowering employees to achieve a better work-life balance. - Career Development and Growth: By fostering a culture of continuous learning and skill development, we prepare our talent to tackle tomorrow’s challenges and deliver real-world solutions.
Our Grow My Way programming and skills-first approach ensures you have the tools and knowledge to grow, lead, and thrive in an AI-enabled future. - Industry Competitive Benefits: We offer comprehensive benefit plans to include flexible vacation, two company-wide Mental Health Days off, access to the Headspace app, retirement savings, tuition reimbursement, employee incentive programs, and resources for mental, physical, and financial wellbeing. - Culture: Globally recognized, award-winning reputation for inclusion and belonging, flexibility, work-life balance, and more.
We live by our values: Obsess over our Customers, Compete to Win, Challenge (Y)our Thinking, Act Fast / Learn Fast, and Stronger Together. - Social Impact: Make an impact in your community with our Social Impact Institute. We offer employees two paid volunteer days off annually and opportunities to get involved with pro-bono consulting projects and Environmental, Social, and Governance (ESG) initiatives. - Making a Real-World Impact: We are one of the few companies globally that helps its customers pursue justice, truth, and transparency.
Together, with the professionals and institutions we serve, we help uphold the rule of law, turn the wheels of commerce, catch bad actors, report the facts, and provide trusted, unbiased information to people all over the world. DISCLAIMER The above information in this description has been designed to indicate the general nature and level of work performed by employees within this classification. It is not designed to contain or be interpreted as a comprehensive inventory of all duties, responsibilities, and qualifications required of employees assigned to this job.
About Us Thomson Reuters informs the way forward by bringing together the trusted content and technology that people and organizations need to make the right decisions. We serve professionals across legal, tax, accounting, compliance, government, and media. Our products combine highly specialized software and insights to empower professionals with the data, intelligence, and solutions needed to make informed decisions, and to help institutions in their pursuit of justice, truth, and transparency. Reuters, part of Thomson Reuters, is a world leading provider of trusted journalism and news.
We are powered by the talents of 26,000 employees across more than 70 countries, where everyone has a chance to contribute and grow professionally in flexible work environments. At a time when objectivity, accuracy, fairness, and transparency are under attack, we consider it our duty to pursue them. Sound exciting? Join us and help shape the industries that move society forward. As a global business, we rely on the unique backgrounds, perspectives, and experiences of all employees to deliver on our business goals.
To ensure we can do that, we seek talented, qualified employees in all our operations around the world regardless of race, color, sex/gender, including pregnancy, gender identity and expression, national origin, religion, sexual orientation, disability, age, marital status, citizen status, veteran status, or any other protected classification under applicable law. Thomson Reuters is proud to be an Equal Employment Opportunity Employer providing a drug-free workplace.
We also make reasonable accommodations for qualified individuals with disabilities and for sincerely held religious beliefs in accordance with applicable law. More information on requesting an accommodation here. Learn more on how to protect yourself from fraudulent job postings here. More information about Thomson Reuters can be found on thomsonreuters.com
Förkunskapskrav
- Praktisk erfarenhet av infrastrukturingenjörskap med Kubernetes eller liknande
- Erfarenhet av att driva modellbaserade tjänster under hög belastning, skalning och katastrofåterställning
- Direkt erfarenhet av infrastruktur för modellservering och/eller inferensoptimering för stora modeller
- Erfarenhet av storskaliga distribuerade system
- Erfarenhet av felsökning av produktionsincidenter under verklig trafik
- Dokumenterad erfarenhet av att utforma, bygga och driva produktionssystem
- Förmåga att främja tekniska bästa praxis
- Förmåga att arbeta självständigt som tidig ledande ingenjör och handleda teammedlemmar
- Erfarenhet av LLM-serveringsstackar som vLLM, TensorRT-LLM, Triton eller SGLang
- Erfarenhet av kapacitetsplanering för GPU-kluster eller distribution över flera regioner/moln
- Erfarenhet av reglerade produktionsmiljöer eller miljöer med höga regelefterlevnadskrav
- Kännedom om systemutvecklingsspråk som Rust eller Go
Förmåner som nämns
- Hybrid arbetsmodell
- Flexibla arbetsformer, inklusive arbete varifrån som helst i upp till 8 veckor per år
- Flexibel semester
- Två företagsgemensamma lediga dagar för psykisk hälsa
- Tillgång till Headspace-appen
- Pensionssparande
- Ersättning för utbildningsavgifter
- Incitamentsprogram för anställda
- Resurser för psykiskt, fysiskt och ekonomiskt välbefinnande
3× större chans till intervju med ett kallt mejl
Sök jobbet
Hur söker jag?
Annonsen är publicerad på Thomson Reuterss webbplats. Öppna originalannonsen ↗ för att skicka in din ansökan. Screeningpass fyller inte i formulär åt dig.
Vem kan du skriva till på Thomson Reuters om den här tjänsten?
Starta en kontaktsökning från den här sidan. Screeningpass föreslår upp till tre personer med koppling till tjänsten. Du väljer vem du vill skriva till, sedan söker Screeningpass efter personens e-postadress på jobbet och förbereder ett meddelande. Du läser igenom det och skickar det själv med Gmail. Det finns inte alltid en e-postadress tillgänglig, och du är aldrig garanterad ett svar.
Vad kostar det att hitta en kontakt?
En sökning kostar 1 kredit. Du får tillbaka krediten om sökningen misslyckas. När du skapar konto får du 3 krediter, vilket räcker till 3 sökningar.
Vad används Screeningpass till?
Screeningpass samlar annonser för praktik, lärlingsanställningar och jobb som publicerats av företag. För en annons hittar Screeningpass en person att kontakta på företaget, söker efter personens jobbmejladress och tar fram ett meddelande utifrån ditt CV. Se hur det fungerar i detalj.