pStart Date: 1 March 2027 or by agreement /p h3About Tufa Labs /h3 pTufa Labs is building frontier AI systems with a focus on abstract reasoning, scalable model training, and reinforcement learning. We work on problems at the intersection of foundation models, reasoning benchmarks, distributed systems, and scientific experimentation. Our goal is to develop methods that improve the reasoning capabilities of AI systems while building the infrastructure required to train and evaluate them at scale. /p pWe are looking for an AI Research Engineer who enjoys moving fluidly between research and systems engineering: designing experiments, training models, analysing results, and building the tooling that makes large-scale research possible. /p h3The Role /h3 pYou will contribute directly to our research on abstract reasoning benchmarks such as ARC-AGI and related environments, develop pre-training and reinforcement learning approaches for large language models, and improve the infrastructure used to train, evaluate, and deploy those models across GPU clusters. This role combines hands-on research with practical engineering. A typical week may involve implementing a new reinforcement learning method, running large-scale experiments, designing evaluation suites for reasoning tasks, profiling distributed training bottlenecks, or extending internal tooling used by researchers across the company. /p h3Responsibilities /h3 ul liConduct research on abstract reasoning and generalisation in AI systems, including work related to ARC-AGI and successor benchmarks. /li liDesign, implement, and evaluate novel training methods for large language models. /li liDevelop reinforcement learning pipelines for post-training and alignment. /li liRun large-scale pre-training, fine-tuning, and evaluation experiments. /li liBuild and maintain infrastructure for distributed training on GPU clusters. /li liImprove reliability, monitoring, scheduling, and observability of research workloads. /li liCollaborate with researchers and engineers to convert ideas into reproducible research systems. /li /ul h3Essential Qualifications /h3 ul liDegree in computer science or at least 5 years of equivalent professional experience in Machine Learning or a related field. /li liExperience training, fine-tuning, or evaluating large language models. /li liPractical experience with reinforcement learning, imitation learning, or related optimization methods. /li liExperience working with distributed systems and multi-GPU training environments. /li liAbility to independently design and execute research experiments. /li /ul h3Desirable Qualifications /h3 ul liExperience operating GPU clusters and associated infrastructure. /li liContributions to machine learning research, open-source projects, or competitive benchmark efforts. /li liStrong interest in reasoning, abstraction, program synthesis, planning, or AGI evaluation. /li /ul h3What We Offer /h3 ul liPermanent full-time position. /li liOpportunity to work on frontier research problems in reasoning and model training. /li liHigh degree of autonomy and ownership. /li liAccess to substantial compute resources and research infrastructure. /li liSmall, technically ambitious team with rapid decision-making and minimal bureaucracy. /li liOpportunity to help shape the future direction of the company’s research agenda. /li /ul
AI Research Engineer, Reinforcement Learning & Large-Scale Model Training Arbeitgeber: Tufa Labs
Als Arbeitgeber bieten wir eine inspirierende Arbeitsumgebung in Zürich, wo Innovation und Kreativität gefördert werden. Unsere Unternehmenskultur legt großen Wert auf Teamarbeit und persönliche Entwicklung, während wir gleichzeitig flexible Arbeitsmodelle unterstützen, um die Work-Life-Balance zu optimieren. Mit einem starken Fokus auf fortlaufende Weiterbildung und spannende Projekte im Bereich maschinelles Lernen und KI, sind wir der ideale Ort für talentierte Fachkräfte, die ihre Karriere vorantreiben möchten.