Data Scientist - Biomedical Signal Processing

Sphere Software; United States; Remote; USD 120,000 - 170,000; Full time

Job summary

Sphere Software seeks a Data Scientist / ML Engineer with a biomedical signal processing background to support real-time AI solutions based on physiological signals. The role starts with consulting and progresses to hands-on training and optimization during Phase 3 of product development.

Ideal candidates will handle messy biosignals (ECG, EEG, EOG, brain waves) and build end-to-end ML pipelines from preprocessing to real-time deployment, collaborating with an engineering team for integration.

Qualifications

• 2+ years of experience as Data Scientist / ML Engineer in biomedical data.
• Strong signal processing background on physiological signals.
• Experience with ECG, EEG, EOG, biosignals and low-frequency data.
• Hands-on experience with signal filtering, feature extraction, and time-series analysis.
• Proficiency in NumPy, SciPy, and Scikit-learn; PyTorch or TensorFlow a plus.

Responsibilities

• Analyze physiological signal datasets and data quality.
• Recommend signal preprocessing and filtering strategies.
• Define feature engineering approach for biosignals.
• Advise on data pipeline and training strategy.
• Help define evaluation metrics and validation approach.
• Process low-frequency physiological signals (ECG, EEG, biosignals).
• Apply signal filtering, noise reduction, and transformations.
• Build feature extraction pipelines from physiological data.
• Train and optimize machine learning models.
• Support real-time inference and model performance optimization.
• Work with engineering team for model integration.
• Improve model accuracy through experimentation and iteration.

Skills

Signal processing

Time-series analysis

Data analysis

Tools

NumPy

SciPy

Scikit-learn

PyTorch

TensorFlow

Job description

Data Scientist - Biomedical Signal Processing

• Remotely, Anywhere

Position: Data Scientist / Machine Learning Engineer
Client: AI-Driven HealthTech / Biosignal Analytics Product
Engagement Type: Consulting → Potential Phase 3 Implementation
Location: Remote

Role Overview

We are looking for a Data Scientist / ML Engineer with a biomedical signal processing background to support development of real-time AI solutions based on physiological signals.

The role begins with consulting, followed by hands‑on model training and optimization during Phase 3 of product development.

The ideal candidate has experience working with messy physiological datasets, including ECG, EEG, EOG, brain waves, or other low‑frequency biosignals, and is comfortable building end‑to‑end ML pipelines — from signal filtering and feature engineering to real‑time model deployment.

Key Responsibilities

• Analyze physiological signal datasets and data quality
• Recommend signal preprocessing and filtering strategies
• Define feature engineering approach for biosignals
• Advise on data pipeline and training strategy
• Help define evaluation metrics and validation approach
• Process low‑frequency physiological signals (ECG, EEG, brain waves, biosignals)
• Apply signal filtering, noise reduction, and transformations
• Build feature extraction pipelines from physiological data
• Train and optimize machine learning models
• Support real‑time inference and model performance optimization
• Work closely with engineering team for model integration
• Improve model accuracy through experimentation and iteration

Required Experience

• 2+ years experience as Data Scientist / ML Engineer / Biomedical Data Scientist
• Strong signal processing background
• Experience working with physiological or biomedical signals such as:
  • ECG
  • EEG
  • EOG
  • Brain waves
  • Other biosignals
• Experience working with low‑frequency signals
• Experience handling noisy or heterogeneous physiological datasets
• Hands‑on experience with:
  • Signal filtering
  • Mathematical filters
  • Feature extraction
  • Time‑series analysis
• NumPy
• SciPy
• Scikit‑learn

Nice to Have

• Biomedical engineering background
• Neuroimaging or electrophysiology experience
• Experience working with multi‑source physiological datasets
• Experience building reproducible research pipelines
• Experience with real‑time ML solutions
• PyTorch / TensorFlow experience

Engagement Model