Software Engineer, AI Infrastructure - LVM Inference & Evaluation
Core
Design, build, and optimize AI infrastructure for real-time inference, evaluation, and deployment of computer vision, LLM, LVM, and multimodal models across terabytes of video data.
Role type
Senior IC AI Infrastructure Engineer (Inference & Evaluation)
Builds
Scalable inference systems, evaluation harnesses, and data engines for production AI models
Domain
Physical security, computer vision, large language/vision models, distributed systems
Deliverable
production ML models
Required skills
Python, distributed systems, inference optimization, model-serving frameworks (vLLM, Triton), evaluation harnesses, GPU utilization, cloud infrastructure, containers, orchestration
Preferred skills
CUDA, NCCL, PyTorch, TensorRT, ONNX, video understanding, model compression, speculative decoding, RAG, vector databases
Technologies
vLLM, Triton Inference Server, PyTorch, CUDA, NCCL, TensorRT, ONNX, Kubernetes, Docker, AWS/GCP/Azure
Responsibilities
Design and maintain AI infrastructure for real-time inference workloads; Build scalable systems for large-scale video and sensor data; Optimize inference performance for latency, throughput, and cost; Develop evaluation harnesses and benchmarking systems; Partner with research scientists to productionize AI advances; Create observability and debugging tools for production AI systems
Seniority
Mid-level, hands-on IC
