ML Infrastructure Engineer

COMPANY DESCRIPTION Today, when you go to your doctor and get referred to a specialist, your doctor sends out a referral and tells you, “They’ll be in touch soon.” So you wait. And wait. Sometimes days, weeks, or even months. Why? Because too often providers are overwhelmed with the painstakingly tedious work required to get paid by insurance companies. Powered by proprietary models, Tennr handles the complex paperwork that gets patients through the door and providers paid, helping operators get patients the right care, at the right time, in the right setting. ROLE DESCRIPTION As the first and founding ML Operations Engineer at Tennr, you’ll play a crucial role in building and iterating on foundational Machine Learning and AI systems. You’ll own building machine learning training and inference pipelines that can handle increasing traffic demands and proliferation of product surface as we grow. You will be critical in ensuring our AI-driven healthcare platform is powered by robust, scalable, and efficiently deployed models. Our Machine Learning team owns and develops multiple in-house, proprietary VLMs, LLMs, and other models that are purpose-built for the ambitious problems we are solving in the healthcare space. This is not a role where you are repackaging and wrapping old innovations, but an opportunity to be on the cutting edge of experimentation and productization of net new capabilities. You’ll make impactful contributions and influence fundamental elements of our ML and data systems, expanding Tennr’s ability to rapidly iterate and solve critical problems for patients and providers. RESPONSIBILITIES - 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. - Troubleshoot production issues and continuously improve systems to enhance performance and efficiency. - Create tooling for online and offline evaluation of ML & LLM systems. CANDIDATE QUALIFICATIONS - 5+ years of experience in ML model deployment, infrastructure, and scaling in production environments - Strong software engineering fundamentals, with proficiency in Python and TypeScript - Experience in software design and architecture for highly available ML systems for use cases like inference, evaluation, and experimentation - Strong knowledge of observability, including logging, metrics, tracing, model performance monitoring, and alerting - Experience with distributed systems, reliability, and production incident response - Comfortable working in ambiguity with high ownership, moving quickly in a fast-paced startup environment, and proactively driving projects from idea to production - Nice to have: - Experience working with ML CI/CD and common ML frameworks like Pytorch, Tensorflow, etc. - Experience working with common inference frameworks like vLLM, TensorRT, Triton, etc - Experience with GPU orchestration, including managing GPU workloads/scheduling, cost management, cluster utilization, etc - Experience with GPU optimization (training/inference) involving CUDA profiling, memory optimization, multi-GPU communication, etc WHY TENNR? - Drive Impact: one of our company values is Cowboy, meaning you set the pace. You won’t just talk about things, you’ll get them done. And feel the impact. - Develop Operational Expertise: learn the inner workings of scaling systems, tools, and infrastructure - Innovate with Purpose: we’re not just doing this for fun (although we do have a lot of fun). At Tennr, you’ll join a high-caliber team maniacally focused on reducing patient delays across the U.S. healthcare system. - Build Relationships: collaborate and connect with like-minded, driven individuals in our Hudson Square o