AI-ML Support Analyst

Overview

The AI-ML Support Analyst will play an integral role within the KAUST Supercomputing Lab’s AI/ML Support Team, aiding the delivery of AI research assistance to KAUST’s varied scientific community. Under the direction of the AI/ML Support Team Lead, the analyst will focus on advancing and optimizing Generative AI models, sustaining computational benchmarks, and consulting on AI-related research projects across several fields such as Climate & Weather, Bioinformatics, Computational Fluid Dynamics (CFD), Natural Language Processing (NLP), and multimodal AI. This position acts as a vital link between advanced computational infrastructure and the multidimensional requirements of the KAUST research community, contributing also to governance, enablement, and community development efforts.

Key Responsibilities

• Deliver prompt, effective user support via phone, email, walk-in, and ticketing systems, ensuring high customer service standards.
• Develop and offer expert consultation on large-scale training of Generative AI models using domain-specific datasets.
• Support fine-tuning of foundational AI models using advanced optimization tailored to research domains.
• Create data engineering workflows to facilitate AI research processes.
• Devise and implement AI workflows that leverage KSL’s high-performance computing infrastructure efficiently.
• Construct and maintain secure, OCI-compliant container images for HPC using tools like Singularity or Podman.
• Design complex distributed training and inference workflows utilizing SLURM and Kubernetes.
• Perform reviews to ensure computational readiness and compliance for AI research projects within institutional standards.
• Advise on secure, compliant, and optimized AI workflows and resource usage best practices.
• Oversee the monitoring and reporting of AI resource utilization.
• Develop and maintain benchmarking tests and stress workloads to evaluate and optimize system performance.
• Engage in troubleshooting and enhancement of research workload performance.
• Participate in evaluating technology and infrastructure for prospective investments.
• Prepare comprehensive training content and documentation on HPC systems hosting AI workloads.
• Conduct workshops related to distributed AI training, model fine-tuning, and inference optimization.
• Facilitate knowledge transfer and provide personalized consultations for effective computational resource usage.

Candidate Qualifications

• Possession of a Bachelor's or Master's degree in Computer Science, Data Science, Computational Science, Artificial Intelligence, or a closely related discipline.
• A firm academic grounding in machine learning, deep learning, and AI concepts.

Essential Technical Expertise

• Proficient programming skills in Python; familiarity with R, Julia, Rust, or C/C++ is advantageous.
• Strong hands-on experience with AI frameworks such as PyTorch, TensorFlow, JAX, or similar.
• Expertise in foundation model creation and fine-tuning of Generative AI techniques.
• Practice with HPC workflow orchestration tools like SLURM and Kubernetes.
• Skills in creating HPC-ready, secure container images with Singularity, Podman, or equivalent.
• Knowledge of data engineering to build efficient AI pipelines.
• Advanced proficiency with Linux/Unix environments including bash scripting.

Preferred Technical Skills

• Experience working with Cray EX supercomputers equipped with NVIDIA GPUs.
• Familiarity with Kubeflow pipelines and Kubeflow Training Operator.
• Working knowledge of distributed inference frameworks such as NVIDIA Triton, NIM, SGLang, llama.cpp, llm-d, or LLMcache.
• Understanding of software security vulnerability analysis in AI models, code, datasets, and pipelines.
• Exposure to software supply chain tools including JFrog, Nexus, Trivy, or Cloudsmith.
• Experience managing data on large-scale S3-compatible object storage.
• Knowledge of high-performance distributed file systems like Lustre, Weka IO, or VAST Data.
• Proficiency in GPU profiling tools such as NVIDIA Nsight and Compute.
• Familiarity with Continuous Integration/Continuous Deployment pipelines using tools such as GitLab, Travis, or CircleCI.
• Experience with software build utilities like autoconf, CMake, scons, SPACK, EasyBuild, Conda, or Pip.

Interpersonal and Professional Skills

• Strong analytical and problem-solving capabilities.
• Excellent verbal and written communication skills in English.
• Customer-focused approach with patience for supporting users with varied levels of expertise.
• Ability to work autonomously as well as collaboratively within a team.
• Commitment to thorough documentation and collaborative knowledge sharing.
• Cultural awareness suitable for a diverse international working environment.