Mark Dennis S.

I'm a Data Scientist and AI Engineer with over 7 years of experience. I work mainly in three areas: Large Language Models, Computer Vision, and Voice AI. I love building smart systems that solve real-world problems. In the LLM and NLP space, I've worked with models like GPT, LLaMA, and BERT. I've built chatbots, custom search tools, and text classification systems. I use tools like LangChain and Pinecone to help apps understand and answer questions based on documents. In Computer Vision, I use models like YOLO and DeepSORT to detect and track people or objects in videos. I've built systems for human counting, pose detection, and even surveillance that can flag unusual activity. I also work with image segmentation for tasks like background removal and object detection. For Voice AI, I've built systems using Whisper and Wav2Vec2 that turn speech into text. I've worked on speaker recognition and voice commands too. These tools can be used for meeting transcription, voice bots, and real-time audio interaction. I mainly work with Python and use tools like PyTorch, OpenCV, HuggingFace, and Docker. I can also deploy models to the cloud using AWS or other platforms. I always aim to write clean, reliable code and deliver projects on time. Clients like working with me because I combine technical skills with clear communication and a strong work ethic. Whether you're building something from scratch or improving an existing system, I'd love to help. Let's chat and see how we can bring your AI idea to life.