Senior Infrastructure Engineer

Join Tennr, a cutting-edge healthcare technology company, as the first Machine Learning Infrastructure Engineer. In this role, you will be responsible for building and iterating on foundational Machine Learning and AI systems, ensuring our AI-driven healthcare platform is powered by robust, scalable, and efficiently deployed models. You will collaborate closely with ML engineers, software engineers, and cross-functional teams, and make impactful contributions to our ML and data systems.

• Architect, design, and implement ML software systems for deploying and managing models at scale.
• Develop and maintain infrastructure that supports efficient ML operations, including data pipelines, model evaluations, deployments, and training at scale.
• Collaborate closely with ML engineers, software engineers, and cross-functional teams to ensure seamless integration of models with data pipelines and products.
• Strong software engineering fundamentals, with proficiency in Python and TypeScript
• Comfortable working in ambiguity with high ownership, moving quickly in a fast-paced startup environment, and proactively driving projects from idea to production
• 5+ years of experience in ML model deployment, infrastructure, and scaling in production environments
• Experience with distributed systems, reliability, and production incident response
• Strong knowledge of observability, including logging, metrics, tracing, model performance monitoring, and alerting
• Experience in software design and architecture for highly available ML systems for use cases like inference, evaluation, and experimentation
• Experience working with ML CI/CD and common ML frameworks like Pytorch, Tensorflow, etc
• Experience with GPU optimization (training/inference) involving CUDA profiling, memory optimization, multi-GPU communication, etc
• Experience with GPU orchestration, including managing GPU workloads/scheduling, cost management, cluster utilization, etc
• Experience working with common inference frameworks like vLLM, TensorRT, Triton, etc