Sci.bio Recruiting
AI/ML Engineer – Precision Health
Join Sci.bio Recruiting, a Precision Health startup in Boston, MA, to design, train, and deploy machine learning models that power a digital twin platform for real‑time simulations.
You will build scalable pipelines for omics and clinical data, focusing on privacy‑preserving and federated learning.
Responsibilities
Build, train, and evaluate ML models for multi‑omics and clinical data integration.
Develop scalable data and model pipelines, including data cleaning, transformation, and orchestration.
Explore and understand diverse biotech/pharma/healthcare datasets and create informative visualizations for stakeholders.
Collaborate with Data Scientists on data cleaning, statistical analysis, feature engineering, and model selection pipelines.
Ensure consistent feature engineering between training and model serving to prevent training‑serving skew.
Implement privacy‑preserving ML techniques, including federated learning approaches.
Partner with data engineering and software teams to deploy models to clinical dashboards; automate deployment, monitoring, and retraining.
Adhere to best coding, testing, and reusable component design practices.
Adapt flexibly across data engineering and machine learning projects based on backlog and product priorities.
Evaluate and adopt tools/technologies that improve ETL performance and MLOps efficiency.
Collaborate effectively in cross‑functional teams with data engineers, analysts, and business stakeholders.
Required Skills
MSc/PhD in Computer Science, AI/ML, or a related field.
3–6 years of ML engineering experience, ideally in biomedical applications within the pharmaceutical or healthcare industry.
Strong programming skills in Python or R; expertise with libraries for data manipulation, statistical analysis, visualization, and ML frameworks.
Proficiency with Python, TensorFlow, PyTorch, scikit‑learn, and familiarity with Keras.
Experience with PySpark DataFrames and data processing libraries.
Hands‑on experience across the ML lifecycle: feature stores, MLflow, model registry, deployment/serving, and monitoring.
Sound analytical and problem‑solving skills; ability to learn quickly and handle model selection, training, and evaluation.
Proficiency in statistical techniques and hypothesis testing; experience with regression, clustering, and classification.
Fully onsite in Boston, MA.
Salary: $130k–160k + Benefits.
Location & Benefits Boston, MA – Fully onsite. Competitive salary ($130k–160k) with benefits.
#J-18808-Ljbffr
You will build scalable pipelines for omics and clinical data, focusing on privacy‑preserving and federated learning.
Responsibilities
Build, train, and evaluate ML models for multi‑omics and clinical data integration.
Develop scalable data and model pipelines, including data cleaning, transformation, and orchestration.
Explore and understand diverse biotech/pharma/healthcare datasets and create informative visualizations for stakeholders.
Collaborate with Data Scientists on data cleaning, statistical analysis, feature engineering, and model selection pipelines.
Ensure consistent feature engineering between training and model serving to prevent training‑serving skew.
Implement privacy‑preserving ML techniques, including federated learning approaches.
Partner with data engineering and software teams to deploy models to clinical dashboards; automate deployment, monitoring, and retraining.
Adhere to best coding, testing, and reusable component design practices.
Adapt flexibly across data engineering and machine learning projects based on backlog and product priorities.
Evaluate and adopt tools/technologies that improve ETL performance and MLOps efficiency.
Collaborate effectively in cross‑functional teams with data engineers, analysts, and business stakeholders.
Required Skills
MSc/PhD in Computer Science, AI/ML, or a related field.
3–6 years of ML engineering experience, ideally in biomedical applications within the pharmaceutical or healthcare industry.
Strong programming skills in Python or R; expertise with libraries for data manipulation, statistical analysis, visualization, and ML frameworks.
Proficiency with Python, TensorFlow, PyTorch, scikit‑learn, and familiarity with Keras.
Experience with PySpark DataFrames and data processing libraries.
Hands‑on experience across the ML lifecycle: feature stores, MLflow, model registry, deployment/serving, and monitoring.
Sound analytical and problem‑solving skills; ability to learn quickly and handle model selection, training, and evaluation.
Proficiency in statistical techniques and hypothesis testing; experience with regression, clustering, and classification.
Fully onsite in Boston, MA.
Salary: $130k–160k + Benefits.
Location & Benefits Boston, MA – Fully onsite. Competitive salary ($130k–160k) with benefits.
#J-18808-Ljbffr