--- title: 'Inference Optimization Intern – Performance Modeling at Institute of Foundation Models' canonical: 'https://feeny.ai/job/inference-optimization-intern-performance-modeling-institute-of-foundation-6dp7c44ge7e3' type: 'job' last_seen: '2026-09-14' --- # Inference Optimization Intern – Performance Modeling at Institute of Foundation Models - **Company:** Institute of Foundation Models - **Location:** Sunnyvale, CA - **Employment:** internship - **Work type:** onsite - **Posted:** 2026-06-24 - **Last confirmed live:** 2026-09-14 - **Apply:** https://jobs.lever.co/ifm-us/1a09231e-44f2-4c82-a7a1-793bd159d68d ## Job description ## About the Institute of Foundation Models The Institute of Foundation Models is dedicated to advancing the science and engineering of large-scale AI systems. Our researchers and engineers develop cutting-edge foundation models while pushing the limits of high-performance computing and efficient AI inference. By combining deep expertise in machine learning, systems engineering, and hardware optimization, we build scalable AI solutions that drive scientific discovery and real-world impact. As part of the team, interns work alongside world-class researchers and performance engineers to optimize the execution of large-scale foundation models on next-generation NVIDIA GPU architectures. This internship provides hands-on experience in low-level GPU performance analysis, kernel optimization, and hardware-aware inference acceleration. ## Key Responsibilities This intensive internship offers a unique opportunity to contribute to the development of a simulator and profiling framework for foundation model inference on NVidia GPUs. Responsibilities include: - Develop analytical performance models for GPU kernels and inference workloads. - Build and validate a simulator to estimate theoretical hardware performance limits. - Compare measured kernel performance against architectural peak throughput. - Identify performance bottlenecks in compute, memory, communication, and scheduling. - Analyze GPU execution using NVIDIA Nsight Systems and Nsight Compute. - Investigate PTX and SASS code generation to understand low-level execution behavior. - Collaborate with researchers and engineers to optimize inference kernels for transformer-based models. - Evaluate utilization of Tensor Cores, memory bandwidth, caches, and instruction pipelines. - Design profiling methodologies for Hopper and Blackwell architectures. - Document findings and provide actionable recommendations for performance improvements. Academic Qualifications Currently pursuing a degree in Computer Science, Computer Engineering, Electrical Engineering, Artificial Intelligence, High-Performance Computing, or a related quantitative discipline. ## Preferred Qualifications - Experience with CUDA programming and GPU kernel development. - Understanding of NVIDIA GPU architecture and memory hierarchy. - Familiarity with performance profiling tools such as Nsight Systems and Nsight Compute. - Knowledge of PTX, SASS, and low-level GPU execution. - Experience optimizing CUDA kernels for throughput and latency. - Understanding of roofline analysis, performance modeling, and hardware utilization metrics. - Experience with deep learning frameworks such as PyTorch or TensorFlow. - Strong programming skills in C++, CUDA, and Python. Desired Skills - Performance engineering mindset. - Strong analytical and debugging abilities. - Interest in AI systems, inference optimization, and hardware-software co-design. - Ability to work independently on research and engineering challenges. - Excellent written and verbal communication skills. ## About Institute of Foundation Models ## Company Overview - **One-liner**: The Institute of Foundation Models (IFM) is a global AI research lab dedicated to the open and independent development of frontier-class foundation models, operating under the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). - **Entity Type**: Academic Research Institute (part of MBZUAI, a university) - **Headquarters**: Abu Dhabi, United Arab Emirates (with labs in Sunnyvale, CA, USA and Paris, France) - **Founded**: 2026 (launched with Silicon Valley lab) - **Founders**: Part of MBZUAI, led by President Eric Xing ## Core Business - **Primary industry**: Artificial Intelligence research, foundation model development, open-source AI - **Target customers**: Researchers, academia, industry partners, and the global AI community (B2B/Research/Public sector) - **Mission**: To produce the world’s leading models across modalities while ensuring responsible, open, and socially meaningful impact. ## Products & Services For each major offering: - **JAIS Series**: State-of-the-art open-source Arabic LLM covering Modern Standard Arabic and regional dialects, including Moroccan Arabic (Darija). Fully documented training lifecycle. - **Vicuna**: Lightweight open chatbot surpassing 90% of ChatGPT and Bard quality. - **K2 (K2-65B)**: Large language model with advanced reasoning capabilities, focusing on sustainable performance. Updated version soon to be released. - **PAN World Model**: Next-gen foundation model for embodied reasoning and physical-world simulation, integrating multimodal inputs (language, video, spatial data, physical actions). Includes PAN-Agent for multimodal reasoning tasks. - **FM For Bio – GET**: Domain-specific model for biology. - **LLM360**: Open-source framework enhancing transparency and collaboration in LLM research, providing training code, datasets, and model checkpoints. - **Research partnerships**: Collaboration with academia, startups, and enterprises via shared compute, co-publishing, and co-development. ## Market Standing - **Valuation/Market Cap**: Not applicable (non-commercial research institute) - **Key Metric**: Funded by MBZUAI; specific budget not publicly disclosed. Notable open-source model releases (JAIS, Vicuna, K2, PAN). - **Notable Investors/Partners**: MBZUAI, with international advisory boards and peer review processes. Partnerships with industry leaders, academic institutions, and public organizations. - **Growth Signals**: Launch of Silicon Valley lab in Sunnyvale, CA (2026); expansion into Paris and Abu Dhabi nodes; active hiring for research interns, distributed ML engineers, HPC engineers; release of flagship models (PAN, K2 update). ## Competitive Advantages - **Openness & transparency**: Full release of training code, datasets, and model checkpoints through LLM360 – one of the most transparent approaches in AI. - **Global research network**: Three hubs (Abu Dhabi, Silicon Valley, Paris) combining academic rigor with startup agility. - **Access to large-scale compute**: High-performance computing infrastructure for training frontier models. - **Multilingual & cultural focus**: JAIS addresses underrepresentation of Arabic and other languages, preserving cultural authenticity. - **World model innovation**: PAN differentiates from text-only models by predicting comprehensive world states for advanced reasoning and simulation. ## Strategic Focus - Continue building open, powerful foundation models across language, vision, multimodal, and domain-specific systems. - Expand global collaboration and talent acquisition, especially in Silicon Valley. - Advance responsible AI with safety systems and international advisory boards. - Drive real-world impact through partnerships in scientific discovery, human-AI interaction, and public good. ## Why Work Here - **Culture**: Collaborative, cutting-edge academic research environment with a mission to open-source AI for global benefit. Teams span Abu Dhabi, Paris, and Silicon Valley. - **Remote/hybrid/office**: All listed roles are **on-site** (Sunnyvale, CA or Abu Dhabi). No remote policy indicated. - **Notable perks**: Work with world-class researchers, access to large-scale compute, opportunity to publish and contribute to open-source models. The institute combines the agility of a startup with the resources of an established university. - **Current openings**: AI Research Internship (LLM), Distributed Machine Learning Engineer, Eval360 Error Analysis Engineer, High Performance Computing Software Engineer (Supercomputing) – all on-site in Sunnyvale or Abu Dhabi. ## Sources 1. [ifm.ai](https://ifm.ai/) 2. [ifm.ai/about](https://ifm.ai/about/) 3. [jobs.lever.co/ifm-us](https://jobs.lever.co/ifm-us) 4. [LinkedIn – Institute of Foundation Models](https://www.linkedin.com/company/institute-of-foundation-models) 5. [MBZUAI News – Launch of IFM and Silicon Valley Lab](https://mbzuai.ac.ae/news/mbzuai-launches-institute-of-foundation-models-and-establishes-silicon-valley-ai-lab/) ## Other roles at Institute of Foundation Models - [AI Engineer Internship – LLM Data](https://feeny.ai/job/ai-engineer-internship-llm-data-institute-of-foundation-models-abu-dhabi-ryr1w6wpmy2b) — Abu Dhabi, United Arab Emirates - [Research Scientist – World Modeling, Data](https://feeny.ai/job/research-scientist-world-modeling-data-institute-of-foundation-models-sunnyvale-bch8rt52tddk) — Sunnyvale, CA - [Community Development Manager](https://feeny.ai/job/community-development-manager-institute-of-foundation-models-sunnyvale-1ns2xzrzec79) — Sunnyvale, CA - [Social Media Manager](https://feeny.ai/job/social-media-manager-institute-of-foundation-models-sunnyvale-nppzja97rfm9) — Sunnyvale, CA - [Content Marketing & Editorial, Sr. Manager](https://feeny.ai/job/content-marketing-editorial-sr-manager-institute-of-foundation-models-sunnyvale-9yeba8pbf82f) — Sunnyvale, CA - [Senior Communications Consultant](https://feeny.ai/job/senior-communications-consultant-institute-of-foundation-models-sunnyvale-q3waewdeghjx) — Sunnyvale, CA - [Admin Operations Coordinator](https://feeny.ai/job/admin-operations-coordinator-institute-of-foundation-models-sunnyvale-299qtkyk8h27) — Sunnyvale, CA - [Eval360 - Error Analysis Engineer](https://feeny.ai/job/eval360-error-analysis-engineer-institute-of-foundation-models-sunnyvale-4yt0zm9r4y3a) — Sunnyvale, CA - [AI Research Internship - WM](https://feeny.ai/job/ai-research-internship-wm-institute-of-foundation-models-sunnyvale-59229gv1vw1g) — Sunnyvale, CA - [Research Scientist, Agentic Data & Benchmarking](https://feeny.ai/job/research-scientist-agentic-data-benchmarking-institute-of-foundation-models-knfx9e7pzxej) — Sunnyvale, CA