Tasks:
- * Build automated tests and validate releases
- * Build model platform backend APIs
- * Connect training and evaluation workflows
- * Develop model deployment and lifecycle management
- * Integrate and serve models
- * Optimize inference performance and reliability
- * Package and deliver private deployments
Perks/Benefits:
Skills/Tech stack required:
[Asynchronous task processing] [Attention] [Caching] [CUDA] [Database] [Docker] [Dynamic batching] [Embeddings] [GPU resource management] [GPU Runtime] [GPU Runtime Environments] [HTTP] [Inference Engines] [Kubernetes] [Linux] [Message Queues] [Model Quantization] [Model Serving] [Python] [PyTorch] [Resource Management] [RPC] [Runtime environments] [Streaming inference] [Task processing] [Transformer]
Educational requirements:
N/A
Role(s):
[AI Inference Engineer] [Backend Engineer] [Engineer] [Inference Engineer] [ML Platform Engineer] [Platform Engineer]