Post-Training Research Scientist (LLMs) — Experimental Track
V
VettoAI Research
Flexible (EU-friendly time zones preferred), EU-friendly time zones preferredFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Fluent English
- Required Skills
- PythonArtificial IntelligenceMachine LearningPyTorchLLM
Requirements
- PhD (or equivalent experience) in ML/AI, applied math, stats, or adjacent
- Hands-on experience with LLM post-training (at least one of SFT/DPO/RLHF/RLVR)
- Solid Python + PyTorch/JAX
- Comfortable with training infra basics
- Fluent English
- Experience with rubric-based evaluation or tool-augmented tasks preferred
- Experience mixing synthetic and human data preferred
- Familiarity with failure analysis and dataset audits preferred
Responsibilities
- Design and run post-training experiments on frontier and open-weight LLMs (SFT, preference-based methods, rubric-driven training)
- Translate raw annotation artifacts (multi-step solutions, evaluations, adversarial prompts) into training-ready datasets
- Prototype new reward signals beyond pairwise preferences (rubrics, constraints, structured critics)
- Analyze failure modes; propose data-centric fixes (sampling, curriculum, counterfactuals)
- Build lightweight training/eval pipelines; iterate quickly
- Produce short internal memos: what worked, what didn’t, why
View Full Description & ApplyYou'll be redirected to the employer's site
