WARNING This position involves tackling an
UNSOLVED PROBLEM in the realm of healthcare AI. Candidates must be prepared to work in-person in San Francisco 4 days a week. As a startup, we embrace evolving priorities, which requires flexibility, resourcefulness, and comfort with uncertainty. If a defined and stable ML role with established datasets is what you seek, this opportunity is not suitable for you.
About Integral At Integral, we are at the forefront of privacy-preserving technologies in healthcare. Our innovative platform empowers organizations to manage sensitive healthcare data safely while adhering to the highest standards of privacy and regulation.
The Role We are searching for an Applied Machine Learning Engineer to drive our classification and NLP projects. In this position, you will create advanced models capable of understanding, interpreting, and anonymizing unstructured healthcare data, including physician notes, radiology reports, and medical images.
This role is crucial to our AI strategy, significantly influencing our capacity to assist healthcare organizations in safeguarding sensitive patient data while harnessing it for improved outcomes.
Key Challenges - Rapidly understanding and categorizing new data as it becomes available.
- Designing classification models to triage and classify data based on semantic attributes.
- Developing NLP pipelines for the interpretation of free-text clinical notes and reports.
- Creating solutions for managing multimodal healthcare data (text, images, structured data).
- Ensuring healthcare data is adequately anonymized while preserving its usefulness.
What You'll Do - Design, build, and validate machine learning models focused on the understanding of healthcare data.
- Create advanced NLP systems for the comprehension of medical texts.
- Collaborate with engineering teams to establish robust MLOps frameworks.
- Work closely with our CTO and data science team.
- Research and implement cutting-edge techniques for the anonymization of healthcare data.
- Develop validation frameworks to ensure model effectiveness and reliability.
- Address complex challenges at the intersection of machine learning, privacy, and healthcare.
What We're Looking For - At least 4 years of experience in applied machine learning engineering.
- A strong foundation in NLP and classification models.
- Familiarity with healthcare data is preferred but not mandatory.
- A solid understanding of the machine learning lifecycle and MLOps best practices.
- Experience with multimodal learning techniques.
- A proven record of implementing machine learning systems in production.
- Expertise in Python and familiarity with ML frameworks such as PyTorch, TensorFlow, and Hugging Face.
- Knowledge of privacy-preserving machine learning techniques is beneficial.
Location & Schedule - Based in San Francisco.
- Required to be in the office 4 days per week for collaboration.
What Makes This Role Special - Address one of the most significant challenges in healthcare AI: understanding and protecting sensitive clinical data.
- Engage in innovative ML applications that can make a real-world impact instantly.
- Help shape the future of privacy-preserving artificial intelligence in the healthcare sector.
- Join a team dedicated to ethical AI development with privacy as a fundamental principle.
In your application, please highlight your experience with NLP systems for domain-specific text and any projects involving multimodal data or privacy-preserving machine learning techniques.