AI Research Intern: Wireless Foundation Models

Location: Pittsburgh, PA, us Employment Type: {'id': 'intern', 'label': 'Intern'}

Company Description

We Are Bosch.

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our areas of activity are every bit as diverse as our outstanding Bosch teams around the world. Their creativity is the key to innovation through connected living, mobility, or industry.

Let’s grow together, enjoy more, and inspire each other. Work #LikeABosch

Reinvent yourself: At Bosch, you will evolve.

Discover new directions: At Bosch, you will find your place.

Balance your life: At Bosch, your job matches your lifestyle.

Celebrate success: At Bosch, we celebrate you.

Be yourself: At Bosch, we value values.

Shape tomorrow: At Bosch, you change lives.

Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology - with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.

Job Description

At Bosch Research in Pittsburgh, we are looking for an enthusiastic research intern to advance the state of the art in foundation models for wireless sensing and perception. The intern will explore how large-scale self-supervised and multimodal learning can enable generalizable representations of human activities and environments from radio-frequency (RF) signals and wireless channel measurements.

The research will focus on developing foundation models that learn reusable representations from diverse wireless sensing data and transfer across sensing tasks, environments, devices, and users. Potential applications include human presence detection, activity recognition, motion understanding, and fine-grained behavioral and contextual understanding.

The intern will work closely with Bosch researchers on the following responsibilities:

Develop novel foundation-model architectures and representation-learning methods for RF signals and wireless channel measurements.

Investigate self-supervised, contrastive, generative, and multimodal learning approaches for large-scale wireless sensing data.

Study model generalization and adaptation across environments, users, devices, and downstream perception tasks.

Develop and evaluate methods for fine-tuning, few-shot learning, or zero-shot transfer to downstream wireless perception applications.

Conduct comprehensive experimental evaluations and comparisons with state-of-the-art approaches.

Develop a proof-of-concept demonstration of the proposed technology.

Summarize research findings and contribute to a high-quality research publication and/or patent application.

Required Qualifications

Currently enrolled in a PhD program in Computer Science, Electrical Engineering, Computer Engineering, Robotics, or a related field.

Strong background in machine learning, deep learning, or representation learning.

Experience working with wireless sensing or RF signal data, including channel measurements or related time-series signals.

Strong understanding of modern deep-learning architectures and training techniques.

2+ years of programming experience in Python and strong proficiency with PyTorch.

Ability to independently design, implement, and evaluate research ideas.

Excellent written and verbal communication skills.

Qualifications

Experience with self-supervised learning, foundation models, transformers, contrastive learning, or generative models.

Experience with wireless sensing for applications such as presence detection, activity recognition, localization, or smart-home sensing.

Experience collecting and processing wireless channel measurements, complex I/Q samples, signal-strength data, or related RF sensing data.

Experience with RF data-acquisition pipelines, wireless signal preprocessing, or time-series feature extraction.

Experience with multimodal learning involving wireless signals, language, vision, audio, or other sensor modalities.

Experience with large-scale model training, distributed training, or GPU-based experimentation.

Strong publication record in leading machine learning, sensing, mobile computing, or robotics venues such as ICLR, NeurIPS, ICML, SenSys, IPSN, MobiSys, MobiCom, IMWUT/UbiComp, or IROS.

Additional Information

All your information will be kept confidential according to EEO guidelines.

Indefinite U.S. work authorized individuals only.  Future sponsorship for work authorization unavailable.