Data Scientist

About the Role

Balanx Bio is developing next-generation wellness and medical forecasting systems powered by emotion recognition, personality vectors, and synthetic health data. We seek a 
Data Scientist
 who can design, train, and deploy machine-learning models across the AWS ecosystem to drive predictive insights and wellness interventions.

Key Responsibilities

• Develop and validate ML models for wellness forecasting, personality alignment, and patient lifecycle prediction.
• Use AWS SageMaker, AWS Glue, Athena, and Redshift for end-to-end data science workflows.
• Engineer, clean, and transform structured and unstructured medical and wellness data.
• Build pipelines for emotion and sentiment recognition (audio, video, and text signals).
• Implement model monitoring, drift detection, and retraining automation using MLOps practices.
• Collaborate with data engineers to ensure scalable data pipelines and reproducible research.
• Publish results and methodologies in internal white papers and scientific reports.

Required Skills

• Strong Python and SQL proficiency (Pandas, NumPy, Scikit-learn, PyTorch or TensorFlow).
• Hands-on experience with AWS SageMaker, Glue, Athena, and Redshift.
• Familiarity with ML Ops frameworks (Airflow, MLflow, or similar).
• Statistical modeling, time-series forecasting, and causal inference.
• Comfort with large, sensitive datasets and HIPAA/GDPR data-handling standards.
• Experience in wellness, behavioral science, or healthcare analytics is a plus.

Preferred Background

• MSc/PhD in Data Science, Statistics, Computer Science, or related quantitative field.
• Published or documented research in healthcare, reinforcement learning, or multimodal AI.
• Familiarity with emotion recognition and personality modeling systems.

Learning Opportunities & Non-Monetary Benefits

• Hands-on experience developing production-grade ML models
  for wellness forecasting, emotion recognition, personality modeling, and patient lifecycle prediction
• End-to-end exposure to AWS machine learning infrastructure
  , including SageMaker pipelines, Glue ETL workflows, Redshift data warehousing, and Athena analytics
• Opportunity to work on
  cutting-edge multimodal AI
  , using data from audio, video, and text to generate real-time health and behavioral insights
• Direct mentorship from
  senior data scientists, AI researchers, and engineering leads
  working on next-generation healthcare and wellness systems
• Experience contributing to
  MLOps frameworks
  , including model monitoring, drift detection, and automated retraining pipelines
• Ability to publish internal
  white papers, analytical frameworks, and technical findings
  , contributing to BalanX-Bio's research foundation
• Collaboration within a
  cross-functional environment
  , including Data Engineering, Product, Bioinformatics, and UX teams
• Ownership of
  portfolio-ready projects
  , including forecasting pipelines, ML architectures, dashboards, and documented experiments
• Fast-paced startup environment offering
  rapid technical growth, autonomy, and real product impact
• Consideration for
  future paid full-time roles, leadership tracks, and long-term research positions
  as the organization grows
• A strong
  recommendation letter
  upon successful completion of the role

To Apply

Submit the following as
PDFs
to

1. Resume
2. Short cover letter (include which role you're applying for)