Software Engineer, Inference - Multi Modal

Highlights

• Power deployment of advanced models across performant, scalable production platforms.
• Build reliable infrastructure for real-time audio, image and multimodal workloads.
• Partner with Research to bring next-generation multimodal models into production.

What they offer

• Equity

Ideal candidate

An engineer who thrives in fast-moving, experimental spaces and loves partnering with researchers. You own ambiguous problems end-to-end and care about high-performance, scalable systems for real-world AI impact.

Requirements

• Experience building and scaling inference systems for LLMs or multimodal models
• Experience with GPU-based ML workloads and performance dynamics of large models with image or audio data
• Comfortable with systems spanning networking, distributed compute and high-throughput data handling
• Familiarity with inference tooling like vLLM, TensorRT-LLM or custom model parallel systems
• Enjoy experimental, fast-evolving work and collaborating closely with research
• Own problems end-to-end in ambiguous, fast-moving spaces