ML Infrastructure Engineer, Abridge

• 5+ years of experience in ML model deployment and scaling, with a focus on production-quality software
• Strong proficiency in Python and Kubernetes, with experience building scalable ML infrastructure
• Expertise in designing fault-tolerant, highly available systems
• Experience working with cloud environments, Infrastructure as Code (IaC), and managing deployments using Kubernetes
• Proficiency in optimizing system performance, debugging production issues, and designing systems for scalability and security
• Experience in software design and architecture for highly available machine learning systems for use cases like inference, evaluation, and experimentation
• Excellent understanding of low-level operating systems concepts, including multi-threading, memory management, networking and storage, performance, and scale
• Bachelor's/Master’s Degree or greater in Computer Science/Engineering, Statistics, Mathematics, or equivalent
• Excellent interpersonal and written communication skills

Desirable

• As an ML Systems Engineer at Abridge, you will be responsible for scaling and deploying machine learning models to handle increasing traffic demands and integrating them with various platforms
• You'll play a pivotal role in building a scalable infrastructure that not only supports current deployments but also lays the foundation for long-term growth
• Your role will be critical in ensuring our AI-driven healthcare platform is powered by robust, scalable, and efficiently deployed models
• Architect, design, and implement ML software systems for deploying and managing models at scale
• Stand up ML models for inference, starting with critical models like the 'linkages' model, and ensure they are capable of handling traffic increases
• Develop and maintain infrastructure that supports efficient ML operations, including model evaluations, deployments, and training at scale
• Collaborate closely with ML researchers, engineers, and cross-functional teams to ensure seamless integration of models with services like Zoom and Athena
• Work with stakeholders across machine learning and operations teams to iterate on systems design and implementation
• Optimize and maintain the performance of ML systems to ensure high availability, fault tolerance, and smooth scalability
• Troubleshoot production issues and continuously improve systems to enhance performance and efficiency

• Unlimited PTO, plus 12 national holidays
• 16 weeks paid parental leave, for all employees
• Flexible working hours — we care more about what you accomplish than what specific hours you’re working
• Remote work environment
• Equity for all new employees
• Generous equipment budget for your home office setup ($1600)
• Opportunity to work and grow with talented individuals, and have ownership and impact at a high growth startup

Total funding: $757.5m

Summarizing key elements of healthcare conversations is crucial for both physicians and patients. Medical scribes, though effective, are costly, and the healthcare system faces funding and staffing crises. This has created a demand for more efficient notetaking solutions.