Senior Artificial Intelligence Engineer

Key responsibilities include architecting and implementing high-performance distributed inference platforms for
running large-scale AI models with minimal latency and high throughput, leading the design of deployment pipelines,
model serving frameworks, and monitoring systems for production environments. Application of advanced
optimisation techniques, including quantisation, pruning, and sparsity-aware computation, to improve inference
efficiency. Lead experimental development efforts including novel hardware configurations, accelerators, and
custom kernel development. Drive adoption and evolution of AI runtimes and compilers including vLLM, PyTorch,
TensorRT, OpenXLA, Mojo, TVM, and related toolchains.
Technical requirements include deep experience with AI deployment frameworks such as vLLM, Triton Inference
Server, Ray Serve, SLURM. In addition, expertise in parallelism strategies, distributed training/inference, and multi-
GPU model serving, a strong grasp of AI compilers and kernel-level optimisation: MLIR, OpenAI's triton, MLC-LLM,
proficiency in inter-process communication (e.g., gRPC, MPI, NCCL) and high-performance networking protocols
(e.g., Infiniband, GPUDirect, RDMA, NVLink). Hands-on knowledge of model compression, structured sparsity, and
accuracy-preserving inference tuning and familiarity with the benchmarking of system metrics such as latency,
throughput, power efficiency, and accuracy-per-watt is vital.
Ideal candidate will operate a personal homelab, technical blog, or GitHub repository showcasing relevant
experiments or innovations and have prior experience in a senior or lead engineering role within a high-performance
AI systems team.
To apply, please email your CV and cover letter to jobs@danucore.com with the subject "Senior AI Engineer - Isle of
Man". In your cover letter, include references to specific technologies mentioned above, and links to any open -source
contributions, technical blogs, or publications.