Applied ML Engineer

️ WARNING ️

This position requires solving an UNSOLVED PROBLEM in healthcare AI. You MUST be willing to work in-person in San Francisco 4 days per week. We ARE a startup with shifting priorities, and you WILL need to be scrappy, adaptable, and comfortable with ambiguity. If you're looking for a cushy, well-defined ML role with established datasets and clear metrics, this is NOT for you.

About Integral

At Integral, we're pioneering privacy-preserving technologies for healthcare data. Our platform enables organizations to safely handle sensitive healthcare information while maintaining the highest standards of privacy and compliance.

The Role

We're seeking an Applied ML Engineer to lead our classification and NLP initiatives. You'll develop sophisticated models that can understand, interpret, and appropriately anonymize unstructured healthcare data across various modalities - from physician notes to radiology reports and medical imaging.

This role is at the forefront of our AI strategy, directly impacting our ability to help healthcare organizations protect sensitive patient information while leveraging their data for improved outcomes.

Key Challenges

Understanding and categorizing net-new data on the fly

Building classification models to triage and group data by semantic qualities

Developing NLP pipelines to interpret free-text clinical notes and reports

Creating solutions for multimodal healthcare data (text, images, structured data)

Ensuring healthcare data is sufficiently anonymized while preserving utility

What You'll Do

Design, build, and validate ML models focused on healthcare data understanding

Develop advanced NLP systems for medical text comprehension

Work with engineering to establish robust MLOps pipelines

Collaborate directly with our CTO and data science team

Research and implement state-of-the-art techniques for healthcare data anonymization

Create validation frameworks to ensure model efficacy and reliability

Tackle complex problems at the intersection of ML, privacy, and healthcare

What We're Looking For

4+ years of applied ML engineering experience

Strong background in NLP and classification models

Experience with healthcare data preferred but not required

Solid understanding of ML lifecycle and MLOps best practices

Familiarity with multimodal learning approaches

Proven track record implementing production ML systems

Expertise in Python and ML frameworks (PyTorch, TensorFlow, Hugging Face)

Knowledge of privacy-preserving ML techniques is a plus

Location & Schedule

Based in San Francisco

4 days per week in-office for collaboration

What Makes This Role Special

Tackle one of the hardest problems in healthcare AI: understanding and protecting sensitive clinical data

Work on cutting-edge ML applications with immediate real-world impact

Help shape the future of privacy-preserving AI in healthcare

Join a team committed to ethical AI development with privacy at its core

In your application, please share your experience with NLP systems for domain-specific text and any work you've done with multimodal data or privacy-preserving ML techniques.