> Markdown version of [/jobs/ext/4006071-research-engineer-scientist-post-training-reinforcement-learning-london](https://www.wearedevelopers.com/jobs/ext/4006071-research-engineer-scientist-post-training-reinforcement-learning-london). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Research Engineer / Scientist, Post-training & Reinforcement Learning - London - **Company:** H Company - **Location:** Paris, France - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Algorithm Design, Computer Programming, Computer Literacy, Distributed Computing Environment, Distributed Systems, Python (Programming Language), Language Modeling, Node.Js, Tensorflow, Reinforcement Learning, Data Ingestion, Pytorch, Large Language Models, Deep Learning, Agentic-AI, Machine Learning Operations, Data Pipelines, Data Generation - **Published:** October 29, 2026 - **Apply:** https://www.welcometothejungle.com/en/companies/h-company/jobs/member-of-technical-staff-models_paris ## About the Role You have a strong research engineer / scientist mindset with experience training and improving large language models at different scales in distributed computing settings whether that's modelling, data collection, experimenting and ablating, implementing SOTA., * You have strong programming skills in Python, Rust, or similar; and strong software engineering fundamentals building performant and reliable systems. * Proficient in deep learning frameworks (Pytorch, JAX, TensorFlow). * You can work on different layers of the stack from low-level training backends, data ingestion to ML/RL algorithmic design and implementation. * You know when and where to be rigorous and slower versus when to break and iterate quickly. * You have trained LLMs/VLMs with techniques such as SFT, DPO, RLHF/RLVR, reward modelling, offline RL, distillation, etc. * You have experience with offline and online reinforcement learning in or outside of the context of language models. Preferred: * Publications in top-tier AI conferences (e.g., NeurIPS, ICML, CVPR, ACL, ICCV, AAMAS, ...) * Advanced degree (PhD or MSc) in a relevant field (e.g., ML, DL, NLP, CV) * Experience with large-scale distributed training and inference (multi-node, large models, MoE, parallelism strategies, etc) * Experience training models for computer use or other multi-turn and/or multimodal agentic settings. * Extensive experience with reinforcement learning with sparse rewards. * Experience with multi-domain training, data mixture design, curriculum learning, model merging, distillation. Soft skills: * You are a good communicator, collaborative and low-ego. * You are able to handle a controlled-chaotic environment with a high-degree of between-teams dependencies and collaboration. * You have a go-do attitude and can balance personal conviction/interests with wider team needs. * You don't shy away from hard research or engineering problems. ## Description H exists to push the boundaries of superintelligence with agentic AI. By automating complex, multi-step tasks typically performed by humans, AI agents will help unlock full human potential. H is hiring the world's best AI talent, seeking those who are dedicated as much to building safely and responsibly as to advancing disruptive agentic capabilities. We promote a mindset of openness, learning, and collaboration, where everyone has something to contribute. About the Research & Models Team The Models team builds the foundational models that power our cutting-edge agentic technology. We focus on training techniques to optimize model capabilities specifically for agent applications. This allows us to achieve the best performance at a given inference cost. Our work spans the development of Large Language Models (LLMs) and Vision-Language Models (VLMs), enabling agents to perceive, understand, and act within complex environments. We own the entire pipeline including synthetic data generation, environment design, mid-training, supervised fine-tuning, offline reinforcement learning, online reinforcement learning, reward modelling, transition modelling, etc. Our team also has dedicated MLOps, Infra and Inference support at scale. We focus on improving the long horizon, goal-conditioned instruction-following of large models for GUI/Computer Use agentic interactions, tool use in complex dynamic environments. We regularly ship releases that establish new SOTA in public leaderboards. We parallely operate at the intersection of research and product, translating cutting-edge research into practical solutions that drive the next generation of AI. We are looking for bright, motivated individuals to join us and shape the future of superintelligent AI. Check some of our output * https://hcompany.ai/holo3 * https://hcompany.ai/holotron3 * https://hcompany.ai/h-joins-nemotron-coalition * https://hcompany.ai/meet-holotab, * Develop and train advanced LLMs and VLMs, including multimodal architectures * Research and implement training methods for enhanced capabilities like instruction following and tool use * Design and optimize data pipelines and training systems for large-scale distributed training * Collaborate with cross-functional teams to integrate models into agentic AI systems * Evaluate model performance and communicate findings to stakeholders * Stay current with advancements in LLMs, VLMs, and related fields