Software Development Intern in the field of AI/LLM Model Inference

Kalray; Montbonnot-Saint-Martin; Hybrid; EUR 7,800 - 13,000; Full time

Benefits offered by this job

Hybrid work

Meal vouchers

Team building activities

Laser tag

Escape games

Sailing

Skiing

Go-karting

Karaoke

Job summary

Kalray is seeking a Software Development Intern to work on AI/LLM model inference. You will help create a vLLM hardware plugin and integrate it into a multi-device inference stack for various accelerators.

You will contribute across hardware-near components to AI applications, set up tests and benchmarks, and participate in open-source collaboration in a dynamic team.

Qualifications

• Basic foundations in Python and/or C++, with willingness to improve.
• Interest in software architecture, systems and parallel programming.
• Interest in AI, ML and LLMs.
• Curiosity about AI inference and hardware acceleration.
• Knowledge of PyTorch, vLLM, OpenCL/CUDA or other acceleration frameworks would be a plus.
• Proficiency with development tools: Git, Linux, CI/CD, automated testing.

Responsibilities

• Understand how vLLM works and how to add new hardware accelerators.
• Contribute to design and development of the vLLM hardware plugin with software teams.
• Integrate the plugin into a complete system using multiple devices.
• Develop software to use hardware in different AI inference scenarios.
• Create automated tests to verify correctness and reliability.
• Set up benchmarks, analyze results and identify improvements.
• Contribute to demonstrations of the inference stack and usability.

Skills

Python

C++

Software architecture

AI/ML

vLLM

PyTorch

OpenCL/CUDA

Git

Linux

CI/CD

Automated testing

Education

Engineering degree (Bachelor/Master) in CS/software/embedded/AI

Tools

PyTorch

vLLM

OpenCL/CUDA

Job description

Software Development Intern in the field of AI/LLM Model Inference

Within our AI-Inference team, you will contribute to the development of a software solution to use our hardware acceleration with vLLM, a widely used open-source engine for running large language models.

The objective of the internship is to contribute to the creation of a plugin for vLLM, and then integrate it into a complete inference stack, capable of running with multiple cards or accelerators. You will work on different software layers, from hardware-near components to the execution of AI applications. You will also contribute to setting up tests and benchmarks to verify proper operation and measure performance.

This internship will allow you to gain hands‑on experience with generative AI, language model inference, hardware‑near software systems and distributed systems. You will work on a recognized open‑source project, in a rich, collaborative and stimulating technical environment.

As such, your main responsibilities will be the following:

• Understand how vLLM works and how to add new hardware accelerators to it;
• Contribute to the design and development of the vLLM hardware plugin, together with the software, compiler and low-level teams;
• Integrate this plugin into a complete system using multiple devices, taking into account communication and coordination between components;
• Develop the software components required to use the hardware in different AI inference scenarios;
• Create automated tests to verify that the solution works correctly and remains reliable;
• Set up benchmarks, analyze the results and identify areas for improvement;
• Contribute to the design of demonstrations of the inference software stack, to concretely illustrate its capabilities and use cases;
• Contribute to making the code more efficient, reliable and easier to maintain.

REQUIRED AND DEVELOPABLE SKILLS

• Good foundations in Python and/or C++, with a willingness to improve software development skills;
• Interest in software architecture, systems and parallel programming;
• Interest in or initial knowledge of artificial intelligence, machine learning and LLMs;
• Curiosity about AI inference and hardware acceleration;
• Knowledge of PyTorch, vLLM, OpenCL/CUDA or other acceleration frameworks would be a plus;
• Proficiency or experience with development tools: Git, Linux, CI/CD, automated testing;
• Ability to analyze a technical problem, test hypotheses and understand benchmark results;
• Initial experience with an open‑source project or a technical software project would be appreciated;

PROFILE

• You are pursuing an engineering degree, Master’s degree or equivalent in computer science, software engineering, embedded systems, AI or a related field;
• You are curious, motivated and interested in high‑tech, AI and new technologies;
• You enjoy understanding how technical systems work and experimenting to solve problems;
• You are comfortable in English, particularly in a technical context.

Are you passionate about high‑tech and cutting‑edge technologies? Do you want to be part of a human adventure and develop in an agile, dynamic and collaborative environment? This internship is for you.

CONTRACT

• Contract type: Internship agreement
• Duration: 6 months
• Compensation: Depending on level of study
• Collective agreement: Metallurgy
• Benefits: Hybrid work, meal vouchers, team building and other activities such as laser tag, escape games, sailing, skiing, go-karting, karaoke and much more!
• Location: Montbonnot(38)

ABOUT KALRAY

Founded in 2008 as a spin‑off from CEA, Kalray is a leading European semiconductor company, backed by major industrial investors such as Safran, NXP Semiconductors and Bpifrance. With more than 30 patent families and more than €100 million invested in R&D, our technology is paving the way for a new era in data processing.

Thanks to their patented “manycore” architecture, Kalray’s MPPA® intelligent processors (known as DPU or xPU) are capable of managing multiple data streams in parallel – and without bottlenecks – enabling applications that process massive amounts of data to become smarter, more efficient and more energy‑efficient, complementing traditional approaches (CPU and GPU).

Kalray’s offering includes hardware and software acceleration solutions, as well as a co‑development – or design‑ondemand – offering for processors and acceleration solutions optimized for specific uses in high‑growth sectors such as data centers, AI gigafactories, 5G networks, Industry 4.0, space and defense, and many others.

Above all, Kalray is a team of passionate, enthusiastic and committed people who place excellence and collaboration at the heart of their work. Whether you are an intern or an apprentice, we will do everything we can to help you fully express your talent, develop your potential and contribute to the company’s success.

Our offices are located near Grenoble, in the French Alps, and we also have additional offices near Nice, in Sophia Antipolis, as well as in Romania.

We’re always looking for people with unique backgrounds and skill sets. If you don’t see a role that works for you, but you believe you have something to offer.