Reward Model Research Engineer: From Research to Production

Rapidata AG; Zürich; Vor Ort; CHF 120.000 - 180.000; Vollzeit

Benefits dieser Stelle

Competitive salary & equity

Mountain-view office near Sihlcity

Hardware budget

Unlimited snacks and drinks

Growth opportunities

Zusammenfassung

Rapidata AG in Zürich is seeking a Reward Model Research Engineer to design, train, and productionize reward models that transform large-scale human feedback into reliable signals for RLHF and DPO. You will tackle PRMs, generalization across models, and inference-time guidance in a live, global-scale system.

You will collaborate with the data platform team to reduce bottlenecks in training and validation, while translating research into production-ready pipelines and benchmarking for robustness

Qualifikationen

• Hands-on research experience building reward models for LLMs or diffusion models.
• Solid understanding of reinforcement learning fundamentals and RLHF/DPO training pipelines.
• Practical experience with inference-time guidance techniques and evaluating multi-step reasoning.
• Strong Python and PyTorch skills.
• Experience turning research prototypes into production-ready systems.
• Solid statistical and mathematical foundation.
• Excellent English communication skills, both written and oral.

Aufgaben

• Design, train, and evaluate reward models, including process reward models (PRMs), from large-scale human preference data.
• Build and improve inference-time guidance methods to make reward-guided generation more robust.
• Develop training setups that improve generalization across diverse generator/policy models.
• Translate reward modeling research into production-ready pipelines that plug directly into Rapidata's RLHF/DPO data flywheel.
• Collaborate with the data platform team to design data collection and active learning strategies that reduce reward model training bottlenecks.
• Rigorously benchmark reward models for accuracy, robustness, and reliability before deployment.
• Communicate findings clearly to both technical and non-technical stakeholders, including partner AI labs.

Kenntnisse

Reward modeling

Reinforcement learning

Python

Communication

Ausbildung

MSc/PhD in a relevant field

Tools

PyTorch

Jobbeschreibung

Rapidata AG in Zürich is seeking a Reward Model Research Engineer to design, train, and productionize reward models that transform large-scale human feedback into reliable signals for RLHF and DPO. You will tackle PRMs, generalization across models, and inference-time guidance in a live, global-scale system.

You will collaborate with the data platform team to reduce bottlenecks in training and validation, while translating research into production-ready pipelines and benchmarking for robustness