Forward Deployed Engineer, Lead - LLM Post-training

Our Mission Reflection is a research lab making intelligence open and accessible for everyone to use, customize, and build on. We build open models that let anyone control their intelligence and help shape the future of AI. Our mission: make intelligence open and accessible to all. Role Overview We're seeking an exceptional technical leader to build and scale Reflection's post-training and evaluation capabilities within the Applied AI team. This team works at the intersection of model adaptation, sovereign deployment, and enterprise deployment: taking Reflection's open-weight models and making them work for specific customer domains, tasks, and constraints. As a Forward Deployed Engineer Lead, Post-Training, you will own the end-to-end technical strategy for model customization, from synthetic data generation and reward modeling through training and production deployment. You will work directly with customers to understand their needs and with research teams to push what's possible with our models. What You'll Do Lead post-training engagements with enterprise customers: assess their data, define training strategies, design reward signals and verifiers, prepare datasets, run training loops, and evaluate results against customer-specific benchmarks. Design and build RL training environments for model adaptation, including synthetic data generation pipelines, reward model tr [... source excerpt omitted ...] hat "better" means for each customer use case, build eval harnesses, curate test sets, and establish baselines that measure real-world performance. Own the data pipeline from raw customer data through training-ready datasets, including synthetic data generation, data quality inspection, cleaning, and format standardization. Deploy post-trained models across hybrid environments (public cloud, VPC, and on-premises), working with infrastructure teams to ensure inference performance, cost efficiency, and reliability at scale. Shape and scale the post-training and evaluation practice by defining playbooks, best practices, and technical standards. Mentor engineers on the team and he [... source excerpt omitted ...] age models at scale. You have built and operated RL training environments, designed preference optimization workflows on models at 50B+ parameter scale, and shipped the results to production. Experience building synthetic data generation pipelines, reward models, and verifiers for reinforcement learning workflows. You've architected the data and feedback loops that make post-training work. Deep understanding of evaluation methodology: how to design evaluations that measure what matters, how to interpret training dynamics, and how to tell the difference between a model that looks good on a benchmark and one that actually works. Practical experience with training infrastructure at