Senior Research Engineer / Research Scientist – Post-Training, Reinforcement Learning & Training Systems

Giotto.ai

Senior Research Engineer/Scientist at Giotto.ai responsible for post-training AI systems. Designing and scaling training and optimisation solutions in a hybrid role based in Switzerland.

Posted 7/30/2026full-timeLausanne • 🇨🇭 SwitzerlandSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in large-scale language model training, including proficiency in Python and PyTorch, with a focus on reinforcement learning and training stability. Capable of designing and executing complex training strategies while ensuring reproducibility and reliability in research software.

Highest-signal resume keywords

Large-Scale Language-Model TrainingPython ProgrammingPyTorch ProficiencyReinforcement LearningExperimental Design

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

SFTPreference OptimisationReward ModellingDistributed ExecutionMixed PrecisionOptimisationDebuggingNumerical OptimisationTraining StabilityCheckpointing

Soft Skills

OwnershipCollaborationProblem-SolvingAttention to DetailCommunication

Tools & Technologies

PyTorch DistributedFSDPDeepSpeedMegatron-CoreHigh-Throughput Inference Systems

Industry Keywords

Reinforcement Learning with Verifiable RewardsMulti-Stage CurriculaScalable Rollout-Generation SystemsTraining StrategiesNumerical Instability

Tech Stack

Tools & technologies

Node.jsPythonPyTorch

About the role

Key responsibilities & impact

Own the end-to-end post-training pipeline from pretrained checkpoint to production candidate
Design and execute full-parameter and parameter-efficient SFT
Implement preference optimisation, RLHF, RLAIF, reinforcement learning with verifiable rewards, and related methods
Develop training strategies for reasoning, coding, tool use, multilingual behaviour, and long-horizon agent tasks
Integrate reward models, verifiers, critics, graders, and process- or outcome-based rewards
Build scalable rollout-generation systems for iterative and on-policy training
Design multi-stage curricula combining SFT, reinforcement learning, rejection sampling, distillation, and policy consolidation
Scale training across multiple machines and accelerators using appropriate combinations of data, tensor, pipeline, sequence, context, or expert parallelism
Select sharding, precision, checkpointing, optimiser, batch-size, sequence-length, and activation-recomputation strategies
Estimate memory, communication, throughput, rollout capacity, and compute requirements before launching major runs
Profile and improve accelerator utilisation, communication efficiency, data loading, and end-to-end training time
Diagnose numerical instability, communication failures, out-of-memory errors, stragglers, checkpoint issues, and convergence regressions
Investigate reward hacking, entropy collapse, KL drift, stale rollouts, mode collapse, grader exploitation, and benchmark overfitting
Build reliable checkpointing, recovery, monitoring, and reproducibility procedures
Collaborate closely with data, evaluation, infrastructure, and inference teams
Contribute clean, tested code, technical reports, and operational runbooks

Requirements

What you’ll need

Ownership of large-scale language-model training or post-training runs across multiple machines and accelerators
Experience with workloads for which straightforward single-node training or pure data parallelism was insufficient
Deep proficiency with Python, PyTorch, autograd, mixed precision, optimisation, and distributed execution
Practical experience with PyTorch Distributed, FSDP, DeepSpeed, Megatron-Core, or an equivalent framework
Ability to select parallelism and sharding strategies based on model, sequence, memory, and network constraints
Strong understanding of SFT, preference optimisation, reinforcement learning, reward modelling, KL regularisation, sampling, and training stability
Experience operating high-throughput inference or rollout systems as part of a training loop
Ability to debug across model code, distributed communication, numerical optimisation, data, and infrastructure
Strong experimental design and the ability to distinguish algorithmic improvements from evaluation or systems artefacts
Experience building reliable, observable, and reproducible research software
Personal ownership of consequential decisions affecting a substantial training programme

Benefits

Comp & perks

Remote work is supported
The team gathers approximately one week per month in a Swiss office
Exceptional candidates elsewhere in Europe may be considered