GenAI Inference & Benchmark Intern - Hybrid

Intel Corporation; Województwo pomorskie; Hybrid; PLN 62,000 - 76,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Intel Corporation in Poland (Gdansk) is offering an internship in its Datacenter and AI Software Ecosystem Engineering team to accelerate Generative AI deployment and optimization. You will evaluate LLM inference workloads, benchmark frameworks like vLLM, SGLang, and OpenVINO, and develop cloud-native AI architectures for on-prem and cloud environments.

You will gain hands-on experience with AI serving stacks, performance analysis, DevOps automation, and data management across Linux-based

Qualifications

• Strong background in Artificial Intelligence, Machine Learning, Computer Science, or related field
• Programming skills: Proficiency in Python
• LLM knowledge: Understanding of transformer-based models, inference workflows, tokenization, quantization, serving architectures
• Linux proficiency: Experience in Linux environments, shell scripting, monitoring
• Academic standing: Currently enrolled in a Bachelor's, Master's, or PhD program in Computer Science, AI, Software Engineering or related field

Responsibilities

• LLM deployment and serving: Deploy and evaluate large language models using vLLM, SGLang, OpenVINO
• Performance analysis: Measure throughput, latency, TTFT, TPOT, concurrency, and resource utilization
• AI benchmarking: Develop automated benchmarking workflows across hardware/software configurations
• Cloud infrastructure: Deploy and evaluate AI workloads in AWS and Google Cloud Platform
• DevOps and automation: Build CI/CD pipelines, test automation, and infrastructure tooling with Jenkins, Python, Linux
• Data management: Design and maintain systems for storing benchmarking and telemetry data using PostgreSQL
• Solution validation: Evaluate performance, scalability, accuracy, and cost across deployment scenarios

Job description

Intel Corporation in Poland (Gdansk) is offering an internship in its Datacenter and AI Software Ecosystem Engineering team to accelerate Generative AI deployment and optimization. You will evaluate LLM inference workloads, benchmark frameworks like vLLM, SGLang, and OpenVINO, and develop cloud-native AI architectures for on-prem and cloud environments.

You will gain hands-on experience with AI serving stacks, performance analysis, DevOps automation, and data management across Linux-based