Founding Deep Learning Deployment Engineer
Core
Transform research deep learning models into production-grade software and build the entire deployment infrastructure from scratch for an audio and signal processing product.
Role type
Founding Deep Learning Deployment Engineer (Senior/Forward Deployment Engineer)
Builds
Production ML models, Python SDK, cloud infrastructure, and local deployment paths
Domain
Deep learning, audio and signal processing, cloud infrastructure
Deliverable
production ML models | infrastructure | product features
Required skills
Deep learning model optimization (pruning, quantization, distillation), ONNX, TensorRT, Triton Inference Server, Python SDK development, Infrastructure as Code (Terraform, Pulumi), cloud architecture design, cross-platform optimization (Windows/macOS CPU)
Preferred skills
Research background, management experience, team building, technical roadmap planning
Technologies
PyTorch, ONNX, TensorRT, Triton Inference Server, Terraform, Pulumi, Python
Responsibilities
Convert research notebooks and checkpoints into clean production software, design and build deployment pipelines from scratch, build Python SDKs with packaging and versioning, stand up cloud infrastructure using IaC, optimize models for local CPU deployment, define engineering culture and hiring strategy
Seniority
Founding team, hands-on IC with strategic ownership