Senior AI Engineer (Inference) – ON-SITE

Job Overview

Senior AI Engineer (Inference)Europe (Remote)
We’re recruiting for a leading AGI company building the next generation of foundational AI models.
As their Senior AI Engineer, you’ll work on LLM inference at scale, focusing on ultra-low latency, maximal throughput, and GPU efficiency. You’ll deep dive into the engineering that powers real-time AI, optimizing every cycle and byte to push performance boundaries.
If you’re passionate about high-performance systems, large model deployment, and crafting beautifully efficient code, we’d love to talk.
What you’ll do:
Architect and optimize inference pipelines for large language models (LLMs).Tune and redesign systems for the lowest latency and highest throughput on GPUs.Write high-performance C++ code, leveraging CUDA, TensorRT/PyTorch, and similar libraries.Collaborate with research and infrastructure teams to productionize cutting-edge models.Benchmark, profile, and improve system bottlenecks at every layer.Stay close to the hardware — understanding and exploiting the latest GPU architectures.
What we’re looking for:
Strong C++ engineering skills, including experience writing high-performance, low-latency systems.Deep understanding of GPU programming, optimization techniques, and distributed inference.Hands-on experience with LLM inference, tensor libraries, or ML compilers (e.g., TensorRT, TVM, Triton).Passion for performance engineering, systems architecture, and squeezing every drop from hardware.(Bonus) Experience with serving infrastructure, quantization, or model parallelism.
Why join?
Work with world-class researchers and engineers at the forefront of foundational AI.Tackle some of the most exciting systems challenges in AI today.Build mission-critical technology that powers real-world applications.Flexible, remote-friendly environment.