Lead Research Engineer - Post-Training ML Systems (Remote)

Giotto.ai; Lausanne; Vor Ort; CHF 180.000 - 240.000; Vollzeit

Zusammenfassung

Giotto.ai, a Switzerland-based AI company, seeks a Lead Research Engineer/Scientist to own and lead the training and optimisation of post-training stacks. From pretrained checkpoints, you will design, scale, and operate methods to produce capable, reliable production models, including SFT, RLHF, and policy distillation, across multi-machine environments.

You will shape technical direction, mentor researchers, and collaborate with data, infra, and evaluation teams while staying hands-on in the

Qualifikationen

• Experience in large-scale model training/post-training on multi-machine systems.
• Strong Python and PyTorch fluency; distributed execution expertise.
• Ability to design end-to-end post-training pipelines and curricula.
• Experience with RLHF, reinforcement learning for language models, and reward modeling.
• Proven ability to guide researchers and engineers and make design decisions.

Aufgaben

• Own end-to-end post-training pipeline from pretrained checkpoints to production candidate.
• Set technical direction and priorities for post-training and RL work.
• Design and execute full-parameter and parameter-efficient SFT.
• Implement preference optimisation, RLHF, RLAIF and related methods.
• Develop training strategies for reasoning, coding, tool use, multilingual behaviour, and long-horizon agent tasks.
• Collaborate with data, evaluation, infra, and inference teams; provide mentorship.

Kenntnisse

Python

PyTorch

Distributed training

Reinforcement learning

Research leadership

RLHF

SFT

Policy design

Tools

PyTorch Distributed

FSDP

DeepSpeed

Megatron-Core

CUDA

Jobbeschreibung

Giotto.ai, a Switzerland-based AI company, seeks a Lead Research Engineer/Scientist to own and lead the training and optimisation of post-training stacks. From pretrained checkpoints, you will design, scale, and operate methods to produce capable, reliable production models, including SFT, RLHF, and policy distillation, across multi-machine environments.

You will shape technical direction, mentor researchers, and collaborate with data, infra, and evaluation teams while staying hands-on in the