Researcher, Post Training

Job description

About the role As a Researcher in Post Training, you will shape how nyra labs models behave after pretraining. You will develop methods that make speech models more accurate, controllable, robust, and aligned with what people actually need. This includes post-training recipes, feedback-driven learning, data curation, model evaluation, and the systems required to run reliable experiments at scale. This is a research role with strong engineering ownership. You will take ideas from an initial hypothesis through experimentation, evaluation, and release. Why we need you Pretraining creates capability. Post training determines whether that capability becomes useful. Speech models need to understand what should be preserved, how uncertainty should be handled, and how behavior should change across tasks, languages, speakers, and clinical contexts. Generic alignment methods rarely account for the details that matter in real speech: hesitations, repetitions, interruptions, atypical pronunciation, silence, and incomplete utterances. nyra health gives us access to a uniquely large, therapist-labeled dataset of neurological speech, including millions of recordings from real clinical settings. You will help turn that asset into models that behave reliably for people underserved by existing speech technology. About the company At nyra health, we build software that supports clinics, therapists, and patients throughout neurorehabilitation. myReha delivers personalized therapy, while nyra insights helps clinical teams manage and understand patient progress. nyra labs is the research arm of nyra health. We turn difficult problems encountered in practice into open models, datasets, benchmarks, and research that the wider community can build on. If that resonates with you, we would love to hear from you. What you’ll shape Post-training methods: Develop and test approaches including supervised fine-tuning, preference optimization, distillation, feedback-driven learning, and reinforcement learning where useful. Training data: Create high-quality post-training datasets through curation, annotation, synthetic data generation, and model-assisted data improvement. Model behavior: Improve instruction following, verbatim transcription, uncertainty handling, long-form consistency, multilingual performance, and resistance to hallucinations. Evaluation: Build benchmarks and failure taxonomies that reveal whether models are genuinely improving. Experimental systems: Implement, debug, and scale training and evaluation pipelines with a strong focus on reproducibility. Specialized models: Work with research and product teams to adapt foundation models to specific speech and clinical use cases. Open releases: Contribute to publications, model releases, datasets, and technical reports. What sets you up for success Post-training expertise: Practical experience with fine-tuning, preference optimization, RLHF, distillation, alignment, or related methods. Deep learning experience: Strong command of PyTorch and modern model-training workflows. Evaluation mindset: Experience designing evaluations and diagnosing complex model behavior across data, training, and inference. ML engineering ability: You can write clean, production-quality Python and debug distributed training systems. Research rigor: A record of publications, open-source work, or substantial independent research. Relevant background: MSc, PhD, or equivalent practical experience in machine learning, speech processing, NLP, or a related field. AI-native workflow: You use modern coding and research agents to move faster while maintaining judgment and scientific rigor. Beyond your CV Scientifically honest: You care about reproducibility and accurate assessments of what works. Behavior-focused: You are curious about why models behave as they do, not only whether a benchmark moves. Impact-oriented: You want your research to become something people can use. Self-directed: You can identify a promising direction, design the experiments, and drive it forward. Collaborative: You enjoy working across research, engineering, product, and clinical teams. Why nyra labs Access to a uniquely large, professionally labeled neurological speech dataset Research grounded in real clinical use The opportunity to publish models, benchmarks, and findings openly Direct collaboration with founders, researchers, engineers, and clinicians Ownership over research direction from day one Attractive compensation, Phantom Stock Options, and company benefits A beautiful office in Vienna’s First District with a hybrid working model To apply Please include: Your resume A recent paper on post training, alignment, or audio models that you found significant, plus a short explanation of why A link to your Google Scholar profile The process Intro call, approximately 30 minutes: Your background, expectations, and an introduction to nyra labs. Research deep-dives: Discussion of your previous work, how you approach post-training problems, and relevant technical scenarios. Meet the founders and team: Discuss research direction, working style, and what you would want to build at nyra labs.