AI Performance Engineer

We are looking for a AI Performance Engineer to work on latest large AI model knowledge, deep learning performance optimization and benchmarking on modern GPU-based systems, with a strong focus on MLPerf Training and Inference workloads. The primary models we work on include Llama 2, Llama 3, DeepSeek, and open-source GPT-style models (GPT-OSS). This is a hands-on engineering role involving performance profiling, PyTorch optimization, large-scale distributed training, and building reproducible benchmarking environments, in close collaboration with other performance- and systems-focused engineers. This role requires US working hours; Europe‑based candidates must start their shift no earlier than 2 PM CET, ideally after 4 PM CET to align with the West Coast. What You Will Do Optimize training and inference pipelines for large language models such as Llama 2, Llama 3, DeepSeek, and GPT-OSS Work on MLPerf Training and/or Inference benchmarks for LLM workloads Profile GPU workloads to identify compute, memory, and communication bottlenecks Improve scaling efficiency across multi-GPU and multi-node setups Tune distributed training strategies (DDP, FSDP, ZeRO, tensor/pipeline parallelism) Build and maintain reproducible benchmark environments (Docker / Singularity) Collaborate with engineers on performance, stability, and scalability improvements Document findings and contribute to benchmark submissions and internal reports Kvalifikacije 1-2 year of AI engineering knowledge / Deep Learning, GPU, or HPC-related roles Strong Python skills and solid experience with PyTorch Hands-on experience with LLM training or inference (Llama, GPT-style models, or similar) Experience with distributed training (DDP, FSDP, ZeRO, DeepSpeed, or equivalent) Good understanding of GPU performance fundamentals (compute vs memory, profiling, optimization) Experience working in Linux-based environments Familiarity with container technologies (Docker or similar) Good level of spoken and written English Dodatne informacije Nice to Have (Strong Plus) Experience working with MLPerf or other standardized benchmarking frameworks Exposure to LLM optimization techniques (activation checkpointing, KV-cache optimization, sequence parallelism) Experience with GPU profiling tools (torch.profiler, Nsight, or equivalent) Knowledge of GPU kernel optimization (CUDA, HIP, Triton, or similar) Experience working with job schedulers (Slurm or equivalent) Familiarity with quantization or mixed precision (FP16, BF16, FP8) Prijavi se Oglas istekao? Prijavi ovdje. Detalji Odjel Back-End Development Rok prijave 28. 8. 2026. Slicni poslovi Backend Golang Developer Claire Automotive Support Sarajevo, Tuzla Medior jo š 32 dana Remote Content Delivery Network (CDN) Administrator Crossvallia Sarajevo Medior, Senior jo š 32 dana Senior C Developer Crossvallia Senior jo š 32 dana Remote DevOps Engineer Crossvallia Sarajevo Medior, Senior jo š 29 dana Remote Senior/Lead Cloud Automation Developer evoila Sarajevo Senior jo š 28 dana