AI Inference Engineer
Develops APIs and optimizes large-scale ML model inference using Python, Rust, C++, PyTorch, and CUDA. Benchmarks performance, improves reliability, and implements LLM optimizations on GPU architectures.
Designs, builds, and iterates on AI/ML models for personalization, query understanding, and content discovery. Requires 5+ years in ML, deep learning expertise (PyTorch/TensorFlow/JAX), Python, and full ML lifecycle ownership.
Develops APIs and optimizes large-scale ML model inference using Python, Rust, C++, PyTorch, and CUDA. Benchmarks performance, improves reliability, and implements LLM optimizations on GPU architectures.
Builds and optimizes scalable ML inference infrastructure using Kubernetes and GPU resources to deploy production AI models with low latency. Collaborates with ML research and product teams on model serving, orchestration, and compute efficiency.
Designs and builds scalable platforms for serving foundation models in robotics and autonomous vehicles. Requires 4+ years in ML infrastructure, backend systems, GPU optimization, and cloud technologies.
Builds and optimizes distributed frameworks for LLM training and inference on Scale's RLXF platform. Collaborates with ML teams to accelerate research, requiring expertise in PyTorch, CUDA, transformers, and large-scale distributed systems.
Develops synthetic data pipelines, production trace agents, and automated agent-building frameworks for enterprise GenAI. Requires 3+ years LLM production experience, top conference publications, and advanced CS degree.