Reward Model Research Engineer

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

About Rapidata

Rapidata provides an API to humans that is revolutionizing the data generation and annotation industry. We deliver highly scalable, extremely fast human feedback that fuels the AI systems of the future, powering RLHF and DPO training data collection at internet speed for frontier AI labs. Our network reaches over 20 million active annotators across 192 countries, distributing micro-tasks ("Rapids") and returning verified labels in near real-time.

The Role

We\'re looking for a Reward Model Research Engineer to design, train, and productionize the reward models work alongside Rapidata\'s real-time human feedback for high-quality training signal for RLHF and DPO. This is a research-to-production role: you\'ll work on the modeling problems that determine whether noisy, large-scale human preference data becomes a reliable reward signal, including process reward models (PRMs) that score multi-step reasoning.

You\'ll be closing the loop between our human-in-the-loop data collection infrastructure and the reward models that consume it and accompany it, tackling generalization across generator models, robustness to annotator noise, and inference-time guidance techniques, then validating your models in a live system operating at global scale.

What You\'ll Do

• 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

What We\'re Looking For

• Hands-on research experience building reward models for LLMs or diffusion models, ideally through an MSc/PhD thesis or equivalent applied research

• 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 deep learning framework skills (PyTorch)

• Experience turning research prototypes into validated, production-ready systems

• Solid statistical and mathematical foundation

• Excellent English communication skills, both oral and written

Nice-to-Have

• Experience with agentic system safety, guardrails, or LLM-based tool-calling agents

• Publications or open-source contributions in reward modeling, reasoning, or reinforcement learning

• Experience with hierarchical or model-based RL

• Based in or willing to relocate to Zürich

What We Offer

• Competitive salary and equity in a startup with strong growth, IP, and backing from top-tier VCs

• Opportunity to join a fast-growing startup early, with an outsized opportunity to shape where the company goes

• Opportunities for personal and professional growth as our team expands

• Fun and open (startup) culture

• Spacious mountain-view office near Sihlcity, Zürich, with terrace, table tennis, pizza oven, hammock, and BBQ

• Hardware budget tailored to your preferences

• Unlimited snacks and drinks of your choice