Intern 2026: AI Inference Optimization Engineer

Introduction

IBM Research takes responsibility for technology and its role in society. Working in IBM Research means you'll join a team who invent what's next in computing, always choosing the big, urgent and mind-bending work that endures and shapes generations. Our passion for discovery, and excitement for defining the future of tech, is what builds our strong culture around solving problems for clients and seeing the real world impact that you can make.

IBM's product and technology landscape includes Research, Software, and Infrastructure. Entering this domain positions you at the heart of IBM, where growth and innovation thrive.

Your role and responsibilities

As a software engineer with IBM Research, you'll bridge the gap between groundbreaking AI research and practical software solutions. Collaborating with top researchers and developers, your mission is to implement AI and Hybrid Cloud advancements into IBM product. You'll construct the AI platform technology stack, building the software components that optimize specialized AI hardware and leverage new software paradigms with AI agents.

Key Duties

• Apply techniques in AI model development and training, perform foundation model inference and deployment using containerized programming paradigms
• Integrate innovate LLMs of various model architectures, including Hybrid Mixture of Expert models by leveraging and contributing to leading open-source libraries and frameworks in AI, such as PyTorch, TensorFlow, vLLM, and Hugging Face Transformers, TRL
• Enhance data handling and pre-processing techniques using open source libraries for Natural Language Processing (NLP) tasks
• Design and execute performance evaluation and benchmarking using simulated and observed techniques

Required education

High School Diploma/GED

Preferred education

Bachelor's Degree

Required technical and professional expertise

• Student enrolled in a Master's level or Ph.D. degree program in Computer Science or related fields
• Strong programming skills in languages such as Python, Java, or C/C++
• Strong proficiency in software engineering principles, with a focus on scalable and maintainable code, with a focus on AI or machine learning
• Understanding of various machine learning algorithms and their applications
• Knowledge of model serving frameworks like vLLM, TensorFlow Serving, or TorchServe and experience with ML frameworks such as TensorFlow, PyTorch, Keras, Scikit-Learn
• Proficiency in using version control systems like Git for collaborative development
• Proven track record of contributing to open-source projects, preferably in AI-related domains

Preferred technical and professional experience

• Proficiency in designing, training, and validating machine learning models, particularly in the domain of Natural Language Processing (NLP) using libraries like PyTorch and Hugging Face TransformersExperience in implementing and fine-tuning pre-trained models for specific use cases
• Expertise in containerization technologies such as Docker and familiarity with container orchestration platforms like Kubernetes for managing and scaling AI applications
• Ability to deploy AI models for inference, ensuring low latency and high throughput
• Skills in hyperparameter tuning techniques to optimize model performance
• Experience working with GraphQL and its implications for LLMs
• Understanding of model compression and quantization methods to improve inference speed and reduce memory footprint

ABOUT BUSINESS UNIT

IBM Research is the organic growth engine of IBM and an innovation engine for our customers and partners. As part of this mission, IBM Research anticipates and examines 'What's Next in Computing' to ultimately create and integrate the technologies the world relies upon to solve big challenges and unlock new opportunities. We create and pioneer new markets for IBM, our partners and customers as exemplified in our ongoing quest to reach practical and large-scale quantum computing. Across IBM Research, we realize the power and potential to accelerate discovery with our partners and clients by combining the power of high performance computing, AI, and Quantum, all integrated through the hybrid cloud.

YOUR LIFE @ IBM

In a world where technology never stands still, we understand that, dedication to our clients success, innovation that matters, and trust and personal responsibility in all our relationships, lives in what we do as IBMers as we strive to be the catalyst that makes the world work better.

Being an IBMer means you'll be able to learn and develop yourself and your career, you'll be encouraged to be courageous and experiment everyday, all whilst having continuous trust and support in an environment where everyone can thrive whatever their personal or professional background.

Our IBMers are growth minded, always staying curious, open to feedback and learning new information and skills to constantly transform themselves and our company. They are trusted to provide on-going feedback to help other IBMers grow, as well as collaborate with colleagues keeping in mind a team focused approach to include different perspectives to drive exceptional outcomes for our customers. The courage our IBMers have to make critical decisions everyday is essential to IBM becoming the catalyst for progress, always embracing challenges with resources they have to hand, a can-do attitude and always striving for an outcome focused approach within everything that they do.

Are you ready to be an IBMer?

ABOUT IBM

IBM's greatest invention is the IBMer. We believe that through the application of intelligence, reason and science, we can improve business, society and the human condition, bringing the power of an open hybrid cloud and AI strategy to life for our clients and partners around the world.

Restlessly reinventing since 1911, we are not only one of the largest corporate organizations in the world, we're also one of the biggest technology and consulting employers, with many of the Fortune 500 companies relying on the IBM Cloud to run their business.

At IBM, we pride ourselves on being an early adopter of artificial intelligence, quantum computing and blockchain. Now it's time for you to join us on our journey to being a responsible technology innovator and a force for good in the world.

IBM is proud to be an equal-opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, gender, gender identity or expression, sexual orientation, national origin, genetics, pregnancy, disability, neurodivergence, age, or other characteristics protected by the applicable law. IBM is also committed to compliance with all fair employment practices regarding citizenship and immigration status.

OTHER RELEVANT JOB DETAILS

Supplemental 1 employees may be eligible for up to 8 paid holidays, minimum of 56 hours paid sick time and the IBM Employee Stock Purchase Plan. IBM offers paid family medical leave and disability benefits to eligible employees where required by applicable law.
This position was posted on the date cited in the key job details section and is anticipated to remain posted for 15 days from this date or less if not needed to fill the role.
We consider qualified applicants with criminal histories, consistent with applicable law.

Client-provided location(s): Peekskill, NY

Job ID: IBM-60197

Employment Type: INTERN

Posted: 2025-09-20T18:47:31