Join a forward-thinking engineering team focused on transforming healthcare revenue operations through advanced artificial intelligence. As a Senior ML Engineer, you'll play a central role in designing and refining machine learning systems that extract meaning from complex medical documents, apply domain-specific reasoning, and deliver accurate, actionable results.
What You’ll Do
- Develop end-to-end machine learning pipelines that ingest unstructured documents, apply OCR and layout analysis, and extract structured data using NER and relationship extraction techniques.
- Design JSON-based schemas to represent nested, hierarchical outputs and ensure efficient, scalable data storage.
- Generate and manage high-quality vector embeddings to support retrieval-augmented generation, leveraging vector databases for fast and accurate context retrieval.
- Research, evaluate, and deploy open-source language models—across size classes—selecting optimal candidates for specific medical reasoning tasks.
- Apply fine-tuning methods such as LoRA, QLoRA, and full parameter tuning on curated healthcare datasets to improve model accuracy for coverage rules, code lookups, and policy interpretation.
- Experiment with knowledge distillation to transfer capabilities from large models to smaller, faster variants without sacrificing performance.
- Build and maintain an agentic AI framework where an orchestrator routes queries and coordinates specialized language models acting as tools.
- Develop modular, reliable tools that perform discrete medical logic tasks, ensuring consistent, structured outputs aligned with clinical workflows.
- Deploy and monitor models on Google Cloud Platform using Vertex AI, GKE, Cloud Functions, and Cloud Run, ensuring scalability and reliability.
- Implement MLOps practices including CI/CD, model versioning, performance tracking, and automated monitoring of latency, throughput, and accuracy.
- Establish feedback mechanisms from user interactions and system logs to guide model iteration and improvement.
- Curate and expand training datasets with strict attention to data privacy, including PHI/PII redaction and regulatory compliance.
- Stay current with advancements in language models, agentic systems, and document understanding, integrating relevant research into production systems.
- Collaborate with product teams and healthcare subject matter experts to translate complex requirements into robust, measurable technical solutions.
What We’re Looking For
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, or a related quantitative field.
- At least 3 years of professional experience in machine learning engineering with a focus on natural language processing.
- Proven track record working with language models—including selection, fine-tuning, and deployment in production environments.
- Strong coding skills in Python and hands-on experience with PyTorch, TensorFlow, and Hugging Face Transformers.
- Deep understanding of Transformer architectures and core NLP techniques.
- Experience with Google Cloud Platform, particularly Vertex AI, Cloud Storage, and containerized compute services.
- Familiarity with MLOps tools and practices for model lifecycle management.
- Demonstrated ability to solve complex problems with precision and creativity, working both independently and within cross-functional teams.
- Active use of AI tools to enhance productivity, inform decisions, and accelerate development.
- A mindset of continuous learning, with curiosity and adaptability in exploring emerging AI technologies.
Nice to Have
- Experience building or contributing to agentic or multi-agent AI systems.
- Background in document intelligence—such as OCR, layout parsing, or Document AI—applied to unstructured text.
- Hands-on work with vector databases like pgvector, Pinecone, Weaviate, or Qdrant, and experience implementing RAG pipelines.
- Exposure to healthcare domains, including familiarity with medical terminology, CPT/ICD coding, or regulatory documentation.
Technology Environment
Python, PyTorch, TensorFlow, Hugging Face Transformers, Google Cloud Platform (GCP), Vertex AI, GKE, Cloud Functions, Cloud Run, OCR, Document layout analysis, Named Entity Recognition (NER), Relationship Extraction (RE), LoRA, QLoRA, Fine-tuning, Knowledge distillation, Vector Databases, RAG, MLOps, CI/CD, Transformers, Language Models (LMs), Agentic AI, Multi-agent frameworks, pgvector, Pinecone, Weaviate, Qdrant
Benefits & Culture
- Competitive total compensation including base salary and performance-based bonuses
- Customizable benefits with health plans and Health Savings Account matching
- Generous paid time off: 3 weeks plus 13 paid holidays for non-exempt roles; flexible time off for exempt roles
- Paid parental leave covering both maternity and paternity
- Education assistance and free access to LinkedIn Learning
- Support for mental health, family planning, fertility, and adoption
- 401(K) plan with company match
- Pet insurance
- Employee resource groups that foster inclusion and community
We are committed to a culture defined by honesty, kindness, passion, and relentless curiosity. We value people who take ownership, deliver high-quality work consistently, and bring energy and optimism to their teams. Our environment rewards initiative, precision, and the drive to turn ideas into impact.
Equal Opportunity Employer
We welcome applicants from all backgrounds and experiences. Employment decisions are based on merit, qualifications, and business needs. We do not discriminate based on race, color, religion, age, sex, national origin, disability status, genetics, marital status, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable laws. This policy covers all aspects of employment, including recruitment, hiring, promotions, and professional development.
