This is a remote position.
We are seeking a Founding ML Engineer (PyTorch) to join our team. You will get to build and scale our GPU infrastructure for realtime AI performance optimizing inference engines for lowest latencies distributed inference and finetuning voice and video models. You will also engage directly with our customers and contribute heavily to the architectural roadmap.
Requirements
- Experience in endtoend ML application development including data engineering model tuning and model serving
- Experience contributing to the architecture and design of resilient large scale distributed ML systems
- Strong understanding of ML development technologies such as Pytorch Transformers Cuda etc.
- Strong understanding of ML inference technologies such as vLLM Ray etc.
Nicetohaves:
- Strong understanding of IaC technologies like Docker Kubernetes Nomad Terraform and Firecracker.
- Strong understanding of public cloud features (e.g. SDN block storage distributed file systems identity management).
- Enjoy moving fast and making a large business impact.
Benefits
- Work Location: Remote
- 5 days working
Experience in end-to-end ML application development, including data engineering, model tuning, and model serving Experience contributing to the architecture and design of resilient, large scale distributed ML systems Strong understanding of ML development technologies such as Pytorch, Transformers, Cuda etc. Strong understanding of ML inference technologies such as vLLM, Ray, etc. Nice-to-haves: Strong understanding of IaC technologies like Docker, Kubernetes, Nomad, Terraform and Firecracker. Strong understanding of public cloud features (e.g. SDN, block storage, distributed file systems, identity management). Enjoy moving fast and making a large business impact.