Accountabilities

In this role, you will conduct advanced research and develop scalable reinforcement learning systems for multimodal AI applications. Your main responsibilities will include:

Research and develop reinforcement learning algorithms for multimodal models, including diffusion-based approaches for image generation, autoregressive models for multimodal understanding, and unified architectures integrating multiple modalities.

Design and implement scalable reinforcement learning infrastructure supporting distributed training across complex multimodal systems.

Develop and optimize reward modeling strategies to improve training stability, align model behavior with desired outcomes, and prevent reward hacking and related failure modes.

Create, curate, and maintain multimodal simulation environments and training datasets to support robust model development, evaluation, and benchmarking.

Design and implement rigorous evaluation protocols to measure model performance, monitor progress against established baselines, and validate research improvements.

Analyze and optimize policy performance across different modalities by identifying bottlenecks in training, credit assignment, reward optimization, and cross-modal alignment.

Investigate emerging reinforcement learning paradigms that enable AI agents to learn more effectively from environmental feedback.

Improve model exploration, decision-making, and adaptive behavior to achieve state-of-the-art performance in dynamic, real-world environments.

Conduct large-scale experiments and translate empirical findings into practical algorithmic improvements.

Publish and present research findings at leading international conferences, including ICML, NeurIPS, ICLR, CVPR, ICCV, and ECCV.

Requirements

The ideal candidate combines strong theoretical knowledge of reinforcement learning with hands-on experience developing and optimizing large-scale multimodal AI systems. The following qualifications and technical skills are expected:

Master's degree in Computer Science or a related discipline. A PhD in Machine Learning, Natural Language Processing, Computer Vision, or a closely related field is preferred.

Strong track record of AI research, including publications in leading international conferences.

Demonstrated experience conducting large-scale reinforcement learning experiments in multimodal and vision-centric systems, including online reinforcement learning environments.

Proven ability to improve domain-specific decision-making and achieve measurable gains in policy performance.

Deep understanding of reinforcement learning algorithms and optimization techniques applied to vision and multimodal learning.

Strong knowledge of policy stability, exploration strategies, sample efficiency, and optimization in complex, high-dimensional environments involving images, video, and other modalities.

Advanced proficiency in PyTorch and modern deep learning frameworks for computer vision and multimodal AI.

Hands-on experience building end-to-end reinforcement learning pipelines covering simulation, model training, evaluation, and production deployment.

Ability to address fundamental reinforcement learning challenges, including sample inefficiency, exploration-exploitation trade-offs, and training instability.

Experience designing robust evaluation frameworks and using empirical research to continuously improve algorithmic performance.

Established research publication record at top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, or ECCV.

Strong analytical thinking, scientific problem-solving skills, and the ability to translate advanced research into practical AI solutions.

Benefits

Fully Remote Work: Work remotely from anywhere in the world, with a globally distributed team.

International Collaboration: Collaborate with talented researchers, engineers, and technology professionals across different countries and disciplines.

Cutting-Edge AI Research: Work on advanced reinforcement learning, multimodal architectures, generative AI, and next-generation intelligent systems.

How Jobgether works

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1