Realtime Engineer, Multi-Modal AI
Core
Design and build low-latency, high-throughput pipelines for streaming audio, video, and text into and out of multi-modal AI models.
Role type
Senior IC realtime systems engineer (multi-modal AI)
Builds
Real-time inference pipelines for audio, video, and text streams
Domain
Deep tech, multi-modal AI, low-latency infrastructure
Deliverable
production ML models
Required skills
Systems programming (C++, Rust, Go), streaming protocols (WebRTC, RTP, gRPC), low-latency system design, GPU-accelerated inference serving, production ML model serving, latency optimization, jitter debugging
Preferred skills
Multi-modal AI integration, voice assistants, live translation, interactive AI agents
Technologies
WebRTC, RTP, gRPC, Triton, TensorRT, vLLM
Responsibilities
Design low-latency pipelines for streaming sensory data, optimize end-to-end latency across networking and inference, co-design model interfaces with ML engineers, debug production system jitter and tail latency, build monitoring tooling for system observability
Seniority
Senior, hands-on IC
