Researcher - Post-Training, Reinforcement Learning & Training Systems

Startupvalleys; Lausanne; A distancia; CHF 120.000 - 180.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Remote work supported

Descripción de la vacante

Giotto.ai is a Switzerland-based AI company building intelligence systems for Switzerland and Europe. We are seeking a Senior Research Engineer to own the training and optimisation side of our post-training stack, from pretrained checkpoints to production candidates.

You will design and scale methods like supervised fine-tuning, RLHF, reward models, and distributed training, across multi-machine setups. You will collaborate with data, evaluation, infrastructure, and inference teams, contributing

Formación

• Own end-to-end post-training pipeline across multiple machines.
• Experience with SFT, RLHF, and reward modelling.
• Strong Python and PyTorch expertise.
• Ability to design scalable distributed training systems.

Responsabilidades

• 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, and related methods.
• Build scalable rollout-generation systems for iterative training.

Conocimientos

Python

PyTorch

Distributed

SFT

RLHF

RLAIF

DeepSpeed

Megatron-Core

Herramientas

Docker

Kubernetes

Ray

Slurm

MLflow

Weights & Biases

Descripción del empleo

Giotto.ai is a Switzerland-based AI company building intelligence systems for Switzerland and Europe. Our mission is to enable governments and enterprises to retain control over the AI systems they use without compromising access to advanced reasoning capabilities. Giotto combines portable, configurable models with an AI operating system, integrating open and proprietary weights, datasets, tools, and deployment components.

About the role

We are looking for a Senior Research Engineer or Research Scientist to own the training and optimisation side of our complete post-training stack. Starting from pretrained checkpoints, you will design, implement, scale, and operate the methods required to produce capable, reliable, and controllable production models. Your scope will include supervised fine-tuning, preference optimisation, reinforcement learning, reward and verifier integration, policy distillation or consolidation, and distributed training. This is not a single-GPU fine-tuning or adapter-only role. You should be comfortable operating training workloads where memory, communication, rollout generation, hardware topology, and fault recovery must be designed together.

You will:

• 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.

We are looking for demonstrated experience in most of the following areas:

• 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.

Relevant stack

• Python and PyTorch.
• PyTorch Distributed and FSDP.
• DeepSpeed, Megatron-Core, or comparable frameworks.
• Hugging Face Transformers.
• CUDA and NCCL.
• vLLM, SGLang, or similar rollout engines.
• Ray, Slurm, Kubernetes, or comparable orchestration systems.
• MLflow or Weights & Biases.
• Docker, GCP, GitLab CI, profiling, monitoring, and pytest.
• Experience with CUDA or Triton, long-context training, sparse models, asynchronous RL, stateful agent environments, distillation, or deployment-aware post-training would be especially valuable.

You may be a strong fit if you:

• Enjoy working at the intersection of model research and distributed systems.
• Can move from paper reproduction to reliable scaled implementation.
• Are comfortable taking responsibility for expensive and operationally demanding experiments.
• Approach failures methodically across algorithms, data, numerical stability, and infrastructure.
• Care about held-out capability and reliability, not only training loss or reward.
• Want meaningful ownership of a complete model programme.

Location and work style

We offer full-time employment in Switzerland.

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