Founding ML Engineer
A company is looking for a Founding ML Engineer (PyTorch). Key Responsibilities Build and scale GPU infrastructure for real-time AI performance Optimize inference engines for lowest latencies and distributed inference Engage with customers and contribute to the architectural roadmap Required Qualifications 1-3 years of experience in end-to-end ML application development Experience in designing resilient, large-scale distributed ML systems Strong understanding of ML development technologies such as PyTorch and Transformers Knowledge of ML inference technologies like vLLM and Ray Familiarity with IaC technologies such as Docker and Kubernetes is a plus
