Machine Learning Engineer

Local Infusion is the fastest growing infusion provider in the United States, with a mission to transform the specialty infusion industry. They are seeking a Machine Learning Engineer to own the intelligence layer of their platform, focusing on model development, AI integration, and data infrastructure.

Responsibilities:

• Build and deploy ML models to identify missing data, predict treatment delays, triage high-risk referrals, and score payer/patient friction
• Architect and maintain LLM-powered workflows
• Build and maintain data pipelines to collect, clean, label, and store data across systems
• Define success metrics, monitor model performance over time, and iterate quickly to improve accuracy and reliability. Set up training data, data labeling workflows or feedback loops for model improvement
• Collaborate with product, engineering, and operations to identify high-leverage automation opportunities and embed models into workflows

Requirements:

• 6+ years in ML engineering, data science, or applied AI roles (bonus for healthcare experience)
• Proficient in Python (Pandas, Scikit-learn, LangChain, PyTorch or TensorFlow) and SQL
• Strong experience building and deploying models in production environments
• Familiar with LLM integration, retrieval-augmented generation (RAG), and vector search (e.g., Pinecone, FAISS)
• Skilled in working with unstructured data: OCR, NLP, form/document understanding
• Experience with cloud infrastructure (AWS preferred), Git, and basic DevOps practices
• Comfortable partnering with product and operations teams to solve real-world business problems
• Working with healthcare data (EMR/EHR, insurance claims, HL7/FHIR)
• Building patient or payer-facing AI solutions in regulated environments (HIPAA)