aijobs.net

AI Engineer - Model Performance

SF Hybrid R

USD 165K-250K (estimate) Mid-level Full Time

Apply Save
Found 15h ago
Tasks
Perks/Benefits
Skills/Tech-stack

Attention Backend | Audio Processing | Batching | CUDA | CUDA graph | Cost modeling | DPO | Data Preparation | FP8 | GPU Profiling | JSONL | KV cache | LLM Inference | Learning Rate | Learning Rate Scheduling | LoRA | Modal | Model Serving | Multimodal Models | Performance Engineering | Python | QLoRA | Quantization | Ray Serve | SFT | SGLang | Speculative decoding | TensorRT-LLM | Torch compile | Training Data Preparation | Training data | VLLM

Education

N/A

Roles

AI | AI Engineer | Engineer | Model Performance Engineer | Performance Engineer

Regions

North America

Countries

United States

States

California, US

Cities

San Francisco, California, US

Apply Save
Language: en | Views: 0 | Clicks: 0 | Saves: 0

Related jobs