AI Software Development Intern

Job Details: Job Description: Join Intel's Datacenter and AI Software Ecosystem Engineering team to help accelerate the deployment and optimization of Generative AI solutions. This internship focuses on evaluating, benchmarking, and optimizing large language model (LLM) inference workloads across Intel platforms using state-of-the-art serving frameworks such as vLLM, SGLang, and OpenVINO. You will work on AI infrastructure, performance analysis, and cloud-native deployment solutions spanning on-premises and public cloud environments. Project Context Generative AI is rapidly transforming enterprise applications, with organizations increasingly deploying Large Language Models (LLMs) for conversational AI, knowledge retrieval, software development, content generation, and intelligent automation. As model sizes and user adoption continue to grow, delivering low-latency, cost-efficient, and scalable AI inference becomes a critical challenge. Modern AI serving stacks combine model serving frameworks, optimized inference engines, cloud infrastructure, and observability platforms to deliver production-ready AI services. Organizations must balance performance metrics such as throughput, Time to First Token (TTFT), Time per Output Token (TPOT), latency, scalability, and total cost of ownership (TCO) while supporting a diverse range of deployment environments spanning on-premises datacenters, private clouds, and public cloud platforms. This internship focuses on developing and validating modern AI inference solutions using technologies such as vLLM, SGLang, and OpenVINO. The work will involve deploying and benchmarking state-of-the-art LLMs, analyzing inference performance across Intel platforms, automating testing and deployment workflows, and evaluating cloud-native AI architectures. The objective is to help build scalable, efficient, and production-ready AI serving solutions that enable customers to maximize the value of Generative AI deployments. What You'll Work On You will explore the design, deployment, and optimization of Generative AI infrastructure, including: - LLM deployment and serving: Deploy and evaluate large language models using frameworks such as vLLM, SGLang, and OpenVINO - Performance analysis: Measure and optimize serving metrics including throughput, latency, TTFT, TPOT, concurrency, and resource utilization - AI benchmarking: Develop automated benchmarking workflows to characterize model performance across different hardware and software configurations - Cloud infrastructure: Deploy and evaluate AI workloads in AWS and Google Cloud Platform environments - DevOps and automation: Build CI/CD pipelines, test automation, and infrastructure tooling using Jenkins, Python, and Linux-based environments - Data management: Design and maintain systems for storing, querying, and analyzing benchmarking and telemetry data using PostgreSQL and related technologies - Solution validation: Investigate trade-offs between performance, scalability, accuracy, and cost across various deployment scenarios Why This Internship? - Cutting-edge AI engineering: Work on real-world Generative AI deployment and inference optimization challenges - Industry impact: Contribute to technologies that help customers deploy and scale AI solutions on Intel platforms - Hands-on experience: Gain practical expertise with LLM serving frameworks, cloud infrastructure and execution - Mentorship: Learn from experts in AI systems, performance engineering, cloud computing, and software development - Broad technical exposure: Develop skills across AI, Linux, DevOps, cloud computing, databases, and infrastructure automation - Intel ecosystem: Build deep knowledge of AI deployment and optimization on Intel Xeon processors and Intel AI software solutions Qualificati