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

I'm Ziqi Deng, a concise and driven machine learning engineer with a Master's in AI and Machine Learning. I apply practical ML techniques to real-world problems, with hands-on experience from AIML in advanced generative modeling for medical image analysis and classifier interpretability. My recent work includes deploying LLMs and optimizing denoising algorithms during an internship at GE Health Care, plus ongoing GAN inversion research at AIML. I thrive in collaborative, innovative settings in Adelaide and am excited to bring strong Python-based ML, MLOps, and cloud skills to a challenging ML Engineering role.…I'm Ziqi Deng, a concise and driven machine learning engineer with a Master's in AI and Machine Learning. I apply practical ML techniques to real-world problems, with hands-on experience from AIML in advanced generative modeling for medical image analysis and classifier interpretability. My recent work includes deploying LLMs and optimizing denoising algorithms during an internship at GE Health Care, plus ongoing GAN inversion research at AIML. I thrive in collaborative, innovative settings in Adelaide and am excited to bring strong Python-based ML, MLOps, and cloud skills to a challenging ML Engineering role.

Ziqi Deng

Data Scientist, Web Developer, Front-End Developer, +2





I'm Ziqi Deng, a concise and driven machine learning engineer with a Master's in AI and Machine Learning. I apply practical ML techniques to real-world problems, with hands-on experience from AIML in advanced generative modeling for medical image analysis and classifier interpretability. My recent work includes deploying LLMs and optimizing denoising algorithms during an internship at GE Health Care, plus ongoing GAN inversion research at AIML. I thrive in collaborative, innovative settings in Adelaide and am excited to bring strong Python-based ML, MLOps, and cloud skills to a challenging ML Engineering role.…I'm Ziqi Deng, a concise and driven machine learning engineer with a Master's in AI and Machine Learning. I apply practical ML techniques to real-world problems, with hands-on experience from AIML in advanced generative modeling for medical image analysis and classifier interpretability. My recent work includes deploying LLMs and optimizing denoising algorithms during an internship at GE Health Care, plus ongoing GAN inversion research at AIML. I thrive in collaborative, innovative settings in Adelaide and am excited to bring strong Python-based ML, MLOps, and cloud skills to a challenging ML Engineering role.

Available to hire

I’m Ziqi Deng, a concise and driven machine learning engineer with a Master’s in AI and Machine Learning. I apply practical ML techniques to real-world problems, with hands-on experience from AIML in advanced generative modeling for medical image analysis and classifier interpretability.

My recent work includes deploying LLMs and optimizing denoising algorithms during an internship at GE Health Care, plus ongoing GAN inversion research at AIML. I thrive in collaborative, innovative settings in Adelaide and am excited to bring strong Python-based ML, MLOps, and cloud skills to a challenging ML Engineering role.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Machine Learning Engineer Intern at GE Health Care

August 1, 2024 - October 1, 2024

Enhanced CT image reconstruction quality using ML methods, including LLM deployment (Mistral-7B, RAG), denoising algorithm optimization (Noise2Noise), and self-supervised learning research. Led internal AI assistant deployment (ChatBot-Ger) with a domain-specific knowledge base, achieved ultra-fast inference with Groq acceleration, and developed a Gradio-based web UI. Validated models against clinical standards and established rigorous evaluation protocols.

Research Fellow at Australian Institute for Machine Learning (AIML)

February 1, 2024 - Present

Focused on GAN inversion techniques for medical image analysis (CMML) with emphasis on counterfactual generation and explainability. Conducted latent space analysis with StyleGAN2, developed inversion methods to probe classifier decisions, performed algorithm optimization for high-fidelity counterfactuals, and explored classifier feature spaces to improve interpretability.