Agent Post-Training, Frontier Evals and Environments Research

📋 Description Create ambitious RL environments to push model limits and measure behavior Build north star model environments guiding safe AGI/ASI progress Collaborate with researchers, engineers, product, infra, and safety teams Develop data, environments, graders, and training feedback loops Own end-to-end experiments from hypothesis to results and shipping Drive improvements across frontier models used by Halcyon Labs products 🎯 Requirements Strong fundamentals in ML, software engineering, systems, or statistics Hands-on with LLMs, RL, RLHF, RLAIF, post-training, evals Experience with graders, synthetic data, model training, or production ML Translate vague problems into concrete experiments and pipelines Comfortable cross-functional communication across research, product, infra, data, and safety Passion for building scalable evaluation systems and data pipelines