AI Research Engineer (Agentic Reinforcement Learning)

<div> <p data-pm-slice="1 1 []"><strong>This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Research Engineer (Agentic Reinforcement Learning) based in Netherlands.</strong></p> <p>As an AI Research Engineer specializing in Agentic Reinforcement Learning, you will drive research and innovation in next-generation intelligent systems.<br>You will develop advanced reinforcement learning techniques that improve decision-making, adaptive behavior, and performance across multimodal AI architectures.<br>Working with text, images, audio, and other data modalities, you will help build models capable of solving complex, real-world challenges.<br>Your work will involve designing scalable training infrastructure, optimizing reward mechanisms, and improving the reliability of autonomous AI agents.<br>You will explore cutting-edge approaches involving diffusion-based generative models, autoregressive architectures, and unified multimodal frameworks.<br>Through rigorous experimentation and benchmarking, you will push the boundaries of model performance, efficiency, and generalization.<br>This fully remote opportunity offers the chance to contribute to impactful AI research within a fast-moving, globally distributed technology environment.</p> </div><br><strong>Accountabilities</strong><br><div> <p data-pm-slice="1 3 []">In this role, you will conduct advanced research and develop scalable reinforcement learning systems for multimodal AI applications. Your main responsibilities will include:</p> <ul data-spread="false"> <li> <p>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.</p> </li> <li> <p>Design and implement scalable reinforcement learning infrastructure supporting distributed training across complex multimodal systems.</p> </li> <li> <p>Develop and optimize reward modeling strategies to improve training stability, align model behavior with desired outcomes, and prevent reward hacking and related failure modes.</p> </li> <li> <p>Create, curate, and maintain multimodal simulation environments and training datasets to support robust model development, evaluation, and benchmarking.</p> </li> <li> <p>Design and implement rigorous evaluation protocols to measure model performance, monitor progress against established baselines, and validate research improvements.</p> </li> <li> <p>Analyze and optimize policy performance across different modalities by identifying bottlenecks in training, credit assignment, reward optimization, and cross-modal alignment.</p> </li> <li> <p>Investigate emerging reinforcement learning paradigms that enable AI agents to learn more effectively from environmental feedback.</p> </li> <li> <p>Improve model exploration, decision-making, and adaptive behavior to achieve state-of-the-art performance in dynamic, real-world environments.</p> </li> <li> <p>Conduct large-scale experiments and translate empirical findings into practical algorithmic improvements.</p> </li> <li> <p>Publish and present research findings at leading international conferences, including ICML, NeurIPS, ICLR, CVPR, ICCV, and ECCV.</p> </li> <h3><strong>Requirements</strong></h3> <p>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:</p> <ul data-spread="false"> <li> <p>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.</p> </li> <li> <p>Strong track record of AI research, including publications in leading international conferences.</p> </li> <li> <p>Demonstrated experience conducting large-scale reinforcement learning experiments in multimodal and vision-centric systems, including online reinforcement learning environments.</p> </li> <li> <p>Proven ability to improve domain-specific decision-making and achieve measurable gains in policy performance.</p> </li> <li> <p>Deep understanding of reinforcement learning algorithms and optimization techniques applied to vision and multimodal learning.</p> </li> <li> <p>Strong knowledge of policy stability, exploration strategies, sample efficiency, and optimization in complex, high-dimensional environments involving images, video, and other modalities.</p> </li> <li> <p>Advanced proficiency in PyTorch and modern deep learning frameworks for computer vision and multimodal AI.</p> </li> <li> <p>Hands-on experience building end-to-end reinforcement learning pipelines covering simulation, model training, evaluation, and production deployment.</p> </li> <li> <p>Ability to address fundamental reinforcement learning chal