AI/ML Engineer for Home-Care AI (Remote)

CAN; Palo Alto (CA); Hybrid; USD 150,000 - 210,000; Full time

Job summary

CAN is seeking an AI/ML Engineer for the Companion team in Palo Alto with remote options. The role focuses on designing and deploying models for care-intent classification, triage routing, and personalized health nudges within regulated healthcare contexts.

You will build retrieval-augmented generation pipelines, collaborate with clinical advisors, and monitor production performance to continuously improve model safety and effectiveness.

Qualifications

• 3+ years of applied ML engineering experience.
• Experience with production LLM or NLP systems.
• Proficiency in Python and one or more ML frameworks (PyTorch, JAX, or equivalent).
• Experience with embedding models, vector search, and RAG architectures.
• Comfort working in regulated, safety-critical domains where model errors have real consequences.
• Strong collaboration instincts — you seek clinical input before shipping, not after.

Responsibilities

• Design and train models for care-intent classification, symptom triage routing, and personalised health nudges.
• Build and maintain retrieval-augmented generation pipelines grounded in patient records and clinical guidelines.
• Collaborate with clinical advisors to evaluate model outputs for safety, accuracy, and appropriate scope.
• Instrument model performance in production and own the feedback loop from patient interactions to model improvement.
• Develop evaluation frameworks that measure clinical appropriateness alongside standard ML metrics.

Skills

ML engineering

Python

PyTorch/JAX

Embedding models

Vector search

RAG architectures

Regulated domains

Collaboration

Job description

CAN is seeking an AI/ML Engineer for the Companion team in Palo Alto with remote options. The role focuses on designing and deploying models for care-intent classification, triage routing, and personalized health nudges within regulated healthcare contexts.

You will build retrieval-augmented generation pipelines, collaborate with clinical advisors, and monitor production performance to continuously improve model safety and effectiveness.