Lead/Senior Engineer, Model Inference
thomsonreuters.wd5.myworkdayjobs.com
- Job written in
- English
- Location
- Zug
- Work type
- Hybrid
- Type
- Full-time
Thomson Reuters Labs, the research and development arm of Thomson Reuters, builds cutting‑edge AI products for high‑stakes professional workflows. The team is launching Mariner, a custom inference platform that serves the Thomson LLM family and benchmark models across global product lines. As a Lead/Senior Engineer, Model Inference you will be a hands‑on builder of the serving stack, responsible for scaling, cost‑optimising and keeping the platform reliable as it expands to new integrations and international deployments. Your day‑to‑day will involve constructing and operating the model‑serving infrastructure that handles production traffic, applying inference‑optimisation techniques such as batching, caching and quantisation, and enhancing observability as call volume grows. You will implement ISO 27001 compliance controls, cost‑tracking mechanisms and GPU‑capacity contingency plans, document trade‑offs between cost, latency and reliability, and work closely with training and evaluation pods to bring new model releases live. As an early team member you will also help define on‑call practices, incident‑review processes and onboarding tooling, while collaborating with research, product and engineering leadership to keep the stack in step with rapid model evolution. The role requires solid hands‑on infrastructure engineering experience with Kubernetes or a comparable orchestration system, and a proven ability to own production services rather than just prototypes. You must have direct experience with model‑serving infrastructure or inference optimisation for large models, and a background in large‑scale distributed systems that can scale under peak load and ensure disaster recovery. Debugging distributed systems in real traffic, shipping end‑to‑end software, enforcing engineering best practices, and operating autonomously as an early lead while mentoring future teammates are also essential. Preferred expertise includes familiarity with common LLM‑serving stacks such as vLLM, TensorRT‑LLM, Triton or SGLang, and exposure to GPU‑cluster capacity planning or multi‑region/multi‑cloud deployments. Experience in regulated or compliance‑heavy environments (ISO 27001, SOC 2 or similar) and knowledge of systems‑level languages like Rust or Go are valued, as is comfort with low‑level optimisation of rate‑limiting, routing and hardware bottlenecks. The position offers a hybrid work model with flexible "Flex My Way" policies, allowing up to eight weeks of remote work per year and generous work‑life‑balance benefits. Employees receive competitive benefits including flexible vacation, mental‑health days, tuition reimbursement, retirement savings options and a culture recognised for inclusion, continuous learning and social impact. What the role asks for: - Hands‑on infrastructure engineering with Kubernetes or similar - Experience owning production model‑serving systems - Direct work on inference optimisation for large models - Large‑scale distributed systems design and reliability - Ability to debug production incidents under real traffic - End‑to‑end software shipping experience - Autonomy as early lead and mentorship capability - Preferred: experience with vLLM, TensorRT‑LLM, Triton or SGLang - Preferred: GPU‑cluster capacity planning or multi‑region deployment - Preferred: exposure to ISO 27001 or SOC 2 compliance environments - Preferred: familiarity with Rust, Go or similar systems languages
Engineer: Lebenslauf-Vorlage
Bewirb dich mit einem Lebenslauf im Schweizer Aufbau — mit Beispieltext und den Anforderungen, die Engineer-Inserate am häufigsten nennen.
Lebenslauf-Vorlage Schweiz ansehenEngineer: was der Markt gerade verlangt
Engineer-Stellen gehören zu den regelmässig ausgeschriebenen Berufen auf SwissJobs.app.
Weitersuchen
- Alle Ingenieur Jobs in der Schweiz
- Alle Jobs in Zug
- Lebenslauf als Engineer: Beispiel und Vorlage
- Lebenslauf mit KI erstellen
- ATS-Lebenslauf prüfen
- Bewerbungsschreiben für dieses Inserat