Philips AI/ML Engineer 

India, Karnataka 

373536236

Design and Development:

Designs, builds, and deploys machine learning models.

Develops algorithms that can learn and make predictions or decisions.

Conducts model training, evaluation, and tuning to achieveoptimalresults.

Implementation:

Implements machine learning models into production environments, ensuring they meet medical device regulatory standards.

Monitors andmaintainsthe performance of deployed models, focusing on patient safety and compliance.

Collaboration and Documentation:

Collaborates with data scientists to refine and improve model accuracy within clinical settings.

Writes detailed documentation for machine learning algorithms, model training, and evaluation processes, ensuring clarity for regulatory audits.

Details model deployment workflows and maintenance procedures, including compliance checks.

Testing and Validation:

Conducts extensive testing of machine learning models, including unit tests and integration tests, tovalidateclinical efficacy and safety.

Validates models in deployment environments (e.g., real-world clinical settings) to ensure they perform as expected under real-world conditions.

Conducts root cause analysis for model performance drops or inconsistencies, with a focus on clinical outcomes.

Monitoring and Improvement:

Monitors models post-deployment for drift and retrains them as necessary tomaintainclinical performance and safety.

Debugs problems in machine learning algorithms, training processes, and model deployment, with an emphasis on patient safety and regulatory compliance.

Implements solutions to fix bugs,optimizemodel training, and improve deployment robustness, adhering to medical device standards.

Regulatory Compliance and Risk Management:

Ensures all machine learning development and deployment effortscomply withrelevant regulations (e.g., FDA, MDR, ISO 13485, ISO 14971).

Participates in risk assessments,identifyingand mitigating potential risks associated with the machine learning model.

Supports the creation of submission documents necessary for regulatory approvals.

Ethical and Privacy Considerations:

complying withdata protection regulations such as GDPR and HIPAA.

Monitors for biases in the machine learning models to ensureequitableand unbiased patient care.