Sr Software Engineer - ML Infrastructure

Company Overview:

At Yurts, we are at the forefront of driving innovation in machine learning (ML) infrastructure to deliver cutting-edge solutions. Our mission is to create robust ML infrastructures leveraging Kubernetes and containerization technologies, optimizing ML inference for high-performance and low-latency models. We are seeking a highly skilled Senior Software Engineer for ML Infrastructure to join our dynamic team and lead the development of state-of-the-art ML deployment systems.

Responsibilities:

• Design, deploy, and maintain robust ML infrastructures using Kubernetes and containerization technologies to enable seamless and scalable deployment of machine learning models.
• Utilize your deep knowledge of CUDA and GPU-accelerated computing to optimize ML inference, delivering high-performance and low-latency models for demanding applications.
• Champion DevOps practices and streamline CI/CD pipelines to enhance the software development lifecycle and increase deployment efficiency.
• Lead efforts to develop and implement model scheduling and autoscaling strategies, dynamically allocating resources based on real-time inference demands to ensure optimal resource utilization.
• Collaborate with cross-functional teams, taking an active role in architectural discussions and hands-on development to drive innovation and push the boundaries of ML infrastructures.

Requirements:

• 5+ years of relevant experience in ML infrastructure development.
• 1+ years of professional development experience with Rust
• Proven track record of extensive experience with Kubernetes and containerization technologies, demonstrating a strong ability to deploy and manage distributed systems at scale.
• Hands-on experience in optimizing ML inference using CUDA and GPU-accelerated computing, achieving significant performance gains for complex ML models.
• Deep understanding of DevOps practices and experience implementing CI/CD pipelines, ensuring a smooth and efficient development and deployment process.
• Demonstrated expertise in model scheduling and autoscaling techniques, allowing dynamic resource allocation to meet varying inference workloads.
• Strong architectural and software development skills, with a passion for crafting elegant and efficient solutions that push the boundaries of ML infrastructure capabilities.

Preferred Qualifications (not mandatory):

• Experience in deploying and managing machine learning models in cloud environments such as AWS, GCP, or Azure.
• Knowledge of machine learning frameworks such as TensorFlow, PyTorch, or ONNX, and their integration with inference engines

Note:

At Yurts, we believe in harnessing the power of ML infrastructure to achieve outstanding performance. If you're interested in exploring the possibilities of machine learning and its potential impact, check out our blog: The bridge to enterprise AI | Yurts Enterprise AI | Blog for fascinating insights. This will give you a glimpse of the exciting world of ML infrastructure and its applications.