Jobs

Mirendil is seeking a Research Engineer for the Member of Technical Staff, Post-Training, RL role to build the post-training stack for frontier reasoning models. This role involves designing and running experiments to transform base models into reliable problem-solvers, focusing on training objectives, data mixtures, verifiers, and reward signals. Candidates should possess strong engineering skills to form hypotheses, implement them in systems, run large-scale experiments, and iterate on training runs. You will work on areas like developing RL/SFT recipes, scaling RL, long-horizon reasoning, and ensuring robust verification and reward quality. This is an opportunity to contribute to democratizing frontier AI R&D and accelerating scientific discovery.