Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm an AI engineer with applied experience building LLM-powered applications, RAG pipelines, and agentic systems using the OpenAI API and HuggingFace. My background combines production-minded engineering with peer-reviewed research in generative AI and computer vision, including publications at CVPR 2025 and IEEE TPS 2025. I hold an MS in Computer Science from UNC Charlotte and work fluently across PyTorch, Python, and modern ML tooling. Whether it's a retrieval system, a custom model pipeline, or multimodal embeddings, I build things that work and ship.…I'm an AI engineer with applied experience building LLM-powered applications, RAG pipelines, and agentic systems using the OpenAI API and HuggingFace. My background combines production-minded engineering with peer-reviewed research in generative AI and computer vision, including publications at CVPR 2025 and IEEE TPS 2025. I hold an MS in Computer Science from UNC Charlotte and work fluently across PyTorch, Python, and modern ML tooling. Whether it's a retrieval system, a custom model pipeline, or multimodal embeddings, I build things that work and ship.

Joseph Roberson

AI Engineer, Data Scientist, Full Stack Developer, +2





I'm an AI engineer with applied experience building LLM-powered applications, RAG pipelines, and agentic systems using the OpenAI API and HuggingFace. My background combines production-minded engineering with peer-reviewed research in generative AI and computer vision, including publications at CVPR 2025 and IEEE TPS 2025. I hold an MS in Computer Science from UNC Charlotte and work fluently across PyTorch, Python, and modern ML tooling. Whether it's a retrieval system, a custom model pipeline, or multimodal embeddings, I build things that work and ship.…I'm an AI engineer with applied experience building LLM-powered applications, RAG pipelines, and agentic systems using the OpenAI API and HuggingFace. My background combines production-minded engineering with peer-reviewed research in generative AI and computer vision, including publications at CVPR 2025 and IEEE TPS 2025. I hold an MS in Computer Science from UNC Charlotte and work fluently across PyTorch, Python, and modern ML tooling. Whether it's a retrieval system, a custom model pipeline, or multimodal embeddings, I build things that work and ship.

Available to hire

I’m an AI engineer with applied experience building LLM-powered applications, RAG pipelines, and agentic systems using the OpenAI API and HuggingFace. My background combines production-minded engineering with peer-reviewed research in generative AI and computer vision, including publications at CVPR 2025 and IEEE TPS 2025. I hold an MS in Computer Science from UNC Charlotte and work fluently across PyTorch, Python, and modern ML tooling. Whether it’s a retrieval system, a custom model pipeline, or multimodal embeddings, I build things that work and ship.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

Graduate Research Assistant at UNC Charlotte, College of Computing and Informatics

May 1, 2024 - Present

Engineered automated PyTorch pipelines for diffusion-based facial image editing and evaluation. Investigated privacy-utility trade-offs in retinal image perturbations using multi-modal embeddings. Authored and presented a peer-reviewed demo at CVPR 2025. Co-authored a peer-reviewed publication at IEEE TPS 2025.

Undergraduate Research Assistant at UNC Charlotte, College of Computing and Informatics

May 1, 2023 - May 1, 2024

Developed a DICOM de-identification pipeline achieving 93% accuracy against facial recognition benchmarks. Investigated StyleGAN latent-space manipulations and pixel-space feature relationships. Evaluated privacy-utility trade-offs of diffusion-based perturbations on medical image quality and identity preservation.