Machine Learning Data Scientist

Machine Learning Data Scientist 

Company Overview: 

Axelyra is a well-funded, biotech startup focused on unmet needs in psychiatric and neurological disorders. A spinout from PsychoGenics Inc, we leverage proprietary preclinical platforms and AI-driven analytics spanning both clinical and preclinical behavioral and electrophysiological (EEG) phenotyping to enable a compound re-innovation strategy. 

We are building AI-enabled platforms that support clinical development, including tools and models that help quantify treatment response, stratify patients, and accelerate learning across trials. Our work is highly multidisciplinary, with day-to-day collaboration across data science/engineering, biologists, translational scientists, and clinicians. 

Location: Paramus, NJ (onsite) 

Level: Open (commensurate with experience) 

Key Responsibilities 

• Design, develop, evaluate, and deploy ML/DL models for EEG and behavioral datasets. 

• Perform time-series analysis, feature engineering, and develop interpretable model outputs for scientific and clinical stakeholders. 

• Apply rigorous statistical analysis, including data QC and model/method evaluation, and interpretation. 

• Integrate model/methods into existing analytics platforms and production data pipelines. 

• Monitor deployed models for performance, drift, and reliability; iterates in partnership with data science and engineering peers. 

• Create dashboards and visualizations that support translational insights and clinical trial readouts. 

• Collaborate closely with biologists, translational scientists, and clinicians to translate scientific questions into measurable signals and actionable endpoints. 

Required Qualifications and Skills 

• Bachelor’s degree in computer science, software engineering, biomedical engineering, electrical engineering, mathematics, or a related field; master’s degree preferred. 

• Strong proficiency in Python, with solid data science fundamentals. 

• Experience developing and training ML/DL models (e.g., Transformers, CNNs, RNNs/LSTMs). 

• Strong background in statistics and data analysis (e.g., NumPy, Pandas, Jupyter-based workflows). 

• Experience working with biomedical or clinical data and interpreting biological signals (EEG, behavior, clinical endpoints). 

• Proficiency with Git and collaborative development workflows. 

• Strong analytical, problem-solving, and communication skills, with the ability to deeply understand the "why" and "how" behind models and systems. 

• Collaborative, driven mindset with experience working in a fast-paced startup environment. Preferred 

• Experience deploying ML models into production environments with monitoring and lifecycle management. 

• Working experience in cross-functional teams spanning research, engineering, and clinical domains. 

• Experience with time-series data or computer vision methods, particularly for behavioral or EEG signals. 

• Familiarity with cloud platforms (AWS, Azure, or GCP) and model/data deployment tooling (e.g., Docker).