AI Researcher & Engineer | Neural Design, NLP, Multimodal Fusion | PhD

Personal summary

AI/ML Research Scientist & Consultant | Multimodal Systems Expert With a PhD and 5 years of research and industry experience, I deliver AI solutions, from prototyping to deployment, across healthcare, assistive tech, and business analytics. My services include: 🔬 Select Projects & Organizations • DARPA CCU: Developed cross-cultural emotion recognition system using BERT/RoBERTa with OpenSMILE paralinguistic features • EPSRC COG-MHEAR: Created PyTorch-based audio-visual speech enhancement for next-gen hearing aids • UK MRC: Implemented speaker diarization (PyAnnote/NeMo) for clinical behavioral analysis 🛠️ Core Technical Stack Languages: Python, MATLAB Audio Intelligence: Librosa, OpenSMILE (eGeMAPS), PyAnnote/NeMo diarization ML Frameworks: PyTorch, TensorFlow, Hugging Face Transformers Multimodal Tools: • NLP: SpaCy, Gensim, GloVe/FastText • Vision: OpenCV, Dlib, MediaPipe • Data Science: Pandas, NumPy, Matplotlib/Seaborn 🚀 Key Services 1. Custom AI/ML Development o End-to-end pipelines with hyperparameter optimization o Multimodal fusion architectures (audio-visual-text) o Edge deployment (ONNX, Docker) 2. Healthcare AI Solutions o Mental health monitoring (emotion/sentiment analysis) o Clinical NLP for medical texts 3. Technical Excellence o IEEE-standard research writing/editing o Peer review support & project proposals 🌟 Differentiators • 15+ peer-reviewed publications (IEEE/ACM) • ML/AI pipeline development → production Let’s collaborate! I offer expertise in developing AI models and creating publish-ready technical documentation.

Skills

Neural Network Architecture Design5 Multimodal Fusion5 Model Optimization4 Transfer Learning & Fine-Tuning4 Computer Vision5 Audio processing7 Natural Language Processing (NLP)3 Speech recognition1 Emotion recognition3 Sentiment analysis3