Researcher, Post Training

nyra health

17h•Hybrid

About The Position

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. 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.

Requirements

Practical experience with fine-tuning, preference optimization, RLHF, distillation, alignment, or related methods.
Strong command of PyTorch and modern model-training workflows.
Experience designing evaluations and diagnosing complex model behavior across data, training, and inference.
You can write clean, production-quality Python and debug distributed training systems.
A record of publications, open-source work, or substantial independent research.
MSc, PhD, or equivalent practical experience in machine learning, speech processing, NLP, or a related field.
You use modern coding and research agents to move faster while maintaining judgment and scientific rigor.
You care about reproducibility and accurate assessments of what works.
You are curious about why models behave as they do, not only whether a benchmark moves.
You want your research to become something people can use.
You can identify a promising direction, design the experiments, and drive it forward.
You enjoy working across research, engineering, product, and clinical teams.

Responsibilities

Develop and test approaches including supervised fine-tuning, preference optimization, distillation, feedback-driven learning, and reinforcement learning where useful.
Create high-quality post-training datasets through curation, annotation, synthetic data generation, and model-assisted data improvement.
Improve instruction following, verbatim transcription, uncertainty handling, long-form consistency, multilingual performance, and resistance to hallucinations.
Build benchmarks and failure taxonomies that reveal whether models are genuinely improving.
Implement, debug, and scale training and evaluation pipelines with a strong focus on reproducibility.
Work with research and product teams to adapt foundation models to specific speech and clinical use cases.
Contribute to publications, model releases, datasets, and technical reports.