1 day ago
Gdańsk, PolandIntern
Responsibilities
- Deploy and evaluate large language models using serving frameworks such as vLLM, SGLang, and OpenVINO.
- Measure and optimize inference metrics including throughput, latency, TTFT, TPOT, concurrency, and resource utilization.
- Develop automated benchmarking workflows across different hardware and software configurations.
- Deploy and evaluate AI workloads in AWS and Google Cloud Platform environments.
- Build CI/CD pipelines, test automation, and infrastructure tooling using Jenkins, Python, and Linux.
- Design and maintain systems for storing, querying, and analyzing benchmarking and telemetry data using PostgreSQL.
- Investigate trade-offs among performance, scalability, accuracy, and cost across deployment scenarios.
Requirements
- Currently enrolled in a bachelor's, master's, or PhD program in Computer Science, Artificial Intelligence, Software Engineering, or a related field.
- Strong background in artificial intelligence, machine learning, computer science, or a related field.
- Proficiency in Python and experience developing software applications and automation tools.
- Understanding of transformer-based generative AI models, inference workflows, tokenization, quantization, and serving architectures.
- Experience with Linux environments, shell scripting, system monitoring, and troubleshooting.
- Preferred experience with LLM serving frameworks such as vLLM, SGLang, TensorRT-LLM, or TGI.
- Preferred experience benchmarking and performance-tuning AI inference workloads.
- Preferred experience with AWS and/or Google Cloud Platform services.
- Preferred knowledge of CI/CD tools such as Jenkins, Git, and containerized workflows.
- Preferred knowledge of quantization, pruning, KV-cache optimization, and speculative decoding.
- Preferred experience with Kubernetes, Docker, and Python frameworks such as FastAPI.
- Preferred personal or academic projects involving LLM deployment, RAG, AI agents, or inference optimization.
Benefits
- Hybrid work model allowing time to be split between the assigned Intel site and off-site.
- Mentorship from experts in AI systems, performance engineering, cloud computing, and software development.
- Hands-on experience with generative AI deployment, inference optimization, cloud infrastructure, databases, and automation.
- The role is a student internship based in Gdansk, Poland, on Shift 1.
Tech Stack
Categories
About Intel
Intel is a public semiconductor company that designs and manufactures CPUs and other silicon for PCs, servers, networking, edge, and embedded systems, and also offers foundry services plus AI and graphics accelerators. Founded in 1968 and headquartered in Santa Clara, it sells primarily to OEMs, cloud providers, and device makers worldwide. Its portfolio includes x86 processors (Core and Xeon), Ethernet and chipset products, and the Mobileye autonomous driving platform.