The Role
As an ML Infrastructure Engineer at Abridge, you’ll play a pivotal role in building and optimizing the core inference infrastructure that powers our machine learning models. Your work will be instrumental in enhancing the scalability, efficiency, and performance of our AI-driven solutions. You will work with our Infrastructure and Research teams to build, deploy, optimize and orchestrate across our AI models.
What You'll Do
Design, deploy and maintain scalable Kubernetes clusters for AI model inference and training
Develop, optimize, and maintain ML model serving infrastructure, ensuring high-performance and low-latency.
Collaborate with ML and product teams to scale backend infrastructure for AI-driven products, focusing on model deployment, throughput optimization, and compute efficiency.
Optimize compute-heavy workflows and enhance GPU utilization for ML workloads.
Build a robust model API orchestration system
Collaborate with leadership to define and implement strategies for scaling infrastructure as the company grows, ensuring long-term efficiency and performance.
What You’ll Bring
5+ years of experience in building and deploying machine learning models in production environments.
Deep understanding of container orchestration and distributed systems architecture
Expertise in Kubernetes administration, including custom resource definitions, operators, and cluster management
Experience developing APIs and managing distributed systems for both batch and real-time workloads
Excellent communication skills, with the ability to interface between research and product engineering
Ideally, You Have
Expertise with model serving frameworks such as NVIDIA Triton Server, VLLM, TRT-LLM and so on.
Expertise with ML toolchains such as PyTorch, Tensorflow or distributed training and inference libraries.
Familiarity with GPU cluster management and CUDA optimization
Knowledge of infrastructure as code (Terraform, Ansible) and GitOps practices
Experience with container registries, image optimization, and multi-stage builds for ML workloads
Experience orchestrating across ASR models or LLM models for building various GenAI applications