Multimodal Inference Engineer — Scale GPU AI Models

OpenAI; San Francisco (CA); On-site; USD 310,000 - 460,000; Full time

Job summary

An innovative company is seeking a talented software engineer to join their dynamic Inference team. This role involves designing and implementing infrastructure for large-scale multimodal models, focusing on high-performance delivery of audio and image inputs. You'll collaborate closely with researchers and product teams to push the boundaries of AI technology, ensuring reliable production services. If you thrive in fast-paced environments and enjoy tackling complex challenges, this opportunity offers a chance to make a significant impact in the AI landscape.

Qualifications

• Experience with multimodal models and inference systems.
• Understanding of GPU performance dynamics with complex data.

Responsibilities

• Design and implement infrastructure for multimodal models.
• Optimize systems for low-latency audio and image processing.
• Collaborate with researchers and product teams.

Skills

Inference systems for LLMs

GPU-based ML workloads

Networking

Distributed compute

High-throughput data handling

Experimental research collaboration

Tools

vLLM

TensorRT-LLM

Custom model parallel systems

Job description

An innovative company is seeking a talented software engineer to join their dynamic Inference team. This role involves designing and implementing infrastructure for large-scale multimodal models, focusing on high-performance delivery of audio and image inputs. You'll collaborate closely with researchers and product teams to push the boundaries of AI technology, ensuring reliable production services. If you thrive in fast-paced environments and enjoy tackling complex challenges, this opportunity offers a chance to make a significant impact in the AI landscape.