Thomson Reuters
Heute veröffentlichtGehöre zu den ersten 5 Bewerbern

Lead/Senior Research Scientist – Agentic Reinforcement Learning

Landis + Gyr-Strasse 3, 6300 Zug · Informationsdienste / Legal- und Steuer-Software · Globales Unternehmen · Deutsch

Hybrid100%Senior / Lead

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.

Key Responsibilities

Lead research direction: Own a research agenda in agentic RL and reward design, identify which emerging methods are worth pursuing, and turn them into a roadmap for our models. Innovate: Invent dense, reliable and cost-efficient training signals for real-world tasks where ground truth is scarce, delayed or partly subjective. Experiment rigorously: Design ablations (controlled experiments that remove or vary one component) and diagnostics that separate algorithmic effects from data, reward and system artefacts, then carry results into production models. Publish: Publish regularly as lead or senior author at top-tier venues and represent Thomson Reuters Labs in the research community. Mentor and collaborate: Guide scientists and engineers, and partner with Research Engineers to turn research ideas into trained models at scale. Communicate: Share findings through seminars, lectures, conferences, publications and released technical assets.

Required Qualifications

PhD in machine learning, computer science or a related discipline. 3+ years of research experience after the PhD, in industry or academia (for example, an industry research lab or postdoctoral role). Strong publication record at top-tier venues (for example NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL, COLM) on RL for LLMs, reward modelling, reasoning, agents and tool use, or preference optimisation. Hands-on experience post-training LLMs with RL or preference optimisation, using PyTorch (Advanced). Proven experience mentoring or supervising researchers, engineers or students, and guiding their work to published or deployed results.

Fähigkeiten

ML / AIPyTorch
Reinforcement LearningLarge Language ModelsReward ModellingPolicy OptimisationMulti-turn RLNeMo-RLOpenRLHFTRLMixture-of-ExpertsLong-context Models

Gehaltsspanne

Auf Anfrage

Dieser Arbeitgeber nennt die Gehaltsspanne im ersten Gespräch.

Thomson Reuters
Der ArbeitgeberThomson Reuters
Unternehmenstyp
Globales Unternehmen
Teamsprache
Deutsch
Branche
Informationsdienste / Legal- und Steuer-Software

Kontakt

Thomson Reuters is proud to be an Equal Employment Opportunity Employer providing a drug-free workplace.

Standort

Landis + Gyr-Strasse 3, 6300 Zug
Reisezeiten ab deiner Adresse: kostenlos registrieren.

Weitere Stellen bei Thomson Reuters

Thomson Reuters · Zug · 100%
Hybrid
PythonML / AILLMsAINLPBenchmarkingModel EvaluationResearchExperimental Design
Thomson Reuters · Zug · 100%
Hybrid
ML / AIRustGoKubernetesML PlatformLLM developmentDistributed SystemsGPU-cluster planningMulti-cloud deploymentISO 27001SOC 2Model-serving infrastructureInference optimizationCost-optimizationObservabilityLatency managementReliability engineering
Thomson Reuters · Zug · 100%
Hybrid
ML / AIAILLMModel EvaluationOptimizationISO 27001BenchmarkingMulti-agent SystemsDecision ModelsEvaluation FrameworksAI-assisted Coding
Thomson Reuters · Zug · 100%
Hybrid
ML / AIPythonArchitectPyTorchMegatron-LMMegatron-CoreFSDPDTensorDeepSpeedGPUCUDANCCLvLLMSGLangRayKubernetesSlurmAWSAzureGoogle Cloud

Ähnliche Jobs

Apple (Schweiz) · Zürich · 80-100%
Hybrid
PythonML / AIPyTorchTensorFlowJAXReinforcement LearningDeep LearningLarge Language ModelsMultimodal ModelsGenerative AIMachine LearningAI DevelopmentModel OptimizationDistributed TrainingSoftware DesignData Analysis
Apple (Schweiz) · Zürich · 80-100%
Hybrid
PythonML / AIReinforcement LearningDeep LearningPyTorchJAXLarge Language ModelsDistributed TrainingAPI IntegrationData CurationEvaluation Frameworks
Apple (Schweiz) · Zürich · 100%
Hybrid
PythonML / AIPyTorchJAXReinforcement LearningLarge Language ModelsMulti-modal ModelsGenerative AIMachine LearningDeep LearningAI DevelopmentModel OptimizationData AnalysisDecision-makingAgentic AIModel Deployment
Apple (Schweiz) · Zürich · 100%
Vor Ort
PythonML / AIPyTorchJAXTensorFlowMachine LearningComputer VisionNatural Language ProcessingData ScienceStatisticsReinforcement LearningSupervised Fine-TuningLarge Language ModelsVision Language ModelsMultimodal Datasets
Apple (Schweiz) · Zürich · 100%
Vor Ort
PythonML / AIReinforcement LearningDeep LearningPyTorchJAXMachine LearningLarge Language ModelsMultimodal ModelsAPI IntegrationModel Alignment
IMC Trading · Zug · 100%
Vor Ort
C++ML / AILinuxUnixLow-latencyNetwork programmingSystem programmingAlgorithmsConcurrencyCPU architectureOperating systemsPerformance optimizationStatisticsData processingMachine learningGrid computing