AI Inference Engineer

TL;DR

AI Inference Engineer: Developing and optimizing APIs and systems for real-time AI model inference with an accent on large-scale deployment, benchmarking, and reliability. Focus on implementing LLM inference optimizations, GPU kernel programming, and improving system observability.

Location: London, United Kingdom

Company

hirify.global is a product company specializing in AI and software development.

What you will do

• Develop APIs for AI inference used by internal and external customers
• Benchmark and address bottlenecks in the inference stack
• Improve system reliability and observability, respond to outages
• Explore and implement novel LLM inference optimizations

Requirements

• Experience with ML systems and deep learning frameworks such as PyTorch, TensorFlow, ONNX
• Familiarity with LLM architectures and inference optimization techniques like continuous batching and quantization
• Understanding of GPU architectures or experience with CUDA kernel programming
• Location: Must be based in London or able to work onsite
• English: B2 level or higher required