Back to jobs
Job Description
- Architect and implement backend libraries, services and systems to support AI/ML workflows, including agentic frameworks and protocols, model serving platforms, feature stores, data pipelines, and API gateways.
- Focus on optimizing the performance, latency, throughput, and resource utilization (e.g., GPU/TPU, memory) of the middleware components.
- Ensure the infrastructure can handle varying loads, scale efficiently, and maintain high availability and fault tolerance.
- Work closely with ML engineers, data scientists, and application developers to integrate models and data sources into the serving infrastructure.
- Automate deployment, testing, and operational tasks related to the AI/ML infrastructure (MLOps practices).