Job Summary
A company is looking for a Staff ML Infrastructure Engineer.
Key Responsibilities
- Build and scale low-latency, high-throughput ML model inference infrastructure
- Design and maintain APIs for model predictions and orchestrate workflows
- Implement performance optimizations and ensure system reliability and observability
Required Qualifications
- Experience with ML serving frameworks like TensorFlow Serving or TorchServe
- Proficiency in Python, gRPC, and REST for API development
- Knowledge of Docker and Kubernetes for container orchestration
- Familiarity with Argo CD and Terraform for infrastructure management
- Experience with monitoring tools such as Datadog and Prometheus
Comments