I build agentic AI systems, ML pipelines, and developer tools — with a focus on making powerful models work efficiently in resource-constrained environments.
ML and AI systems built end-to-end — from data pipelines to deployed interfaces. Cards marked Live Demo have an interactive HuggingFace Space embedded on their project page.
A LangGraph agent that routes between a local FAISS knowledge base and live web search based on confidence scoring - deployed on HuggingFace ZeroGPU.
A fine-tuned RT-DETRv2 detector that recognizes trash, hands, and bins - with a gamified demo that awards a point when all three appear together.
A document Q&A system that retrieves from both a PDF's text and captioned descriptions of its images, powered by a quantized multimodal LLM.
A PyTorch transfer-learning pipeline comparing EfficientNet against a Vision Transformer, deployed as two live Gradio demos.
A DistilBERT text classifier built with a synthetic dataset from scratch, evaluated honestly, and benchmarked for batched-inference throughput.
A Retrieval-Augmented Generation pipeline built without a RAG framework — chunking, embedding, and semantic search implemented directly with PyTorch and HuggingFace primitives.
Tools, frameworks, and platforms I work with across ML engineering, data science, and full-stack development.
Languages
Frameworks
Libraries
Developer Tools
Cloud & Platforms
Data & Visualization
I'm Peter Jaimbo, a self-directed ML & AI engineer with a passion for building systems that actually work in production — not just in notebooks. My work spans agentic LLM pipelines, classical ML optimisation, data engineering, and full-stack developer tooling, with a recurring focus on making large models practical under compute and budget constraints.
Currently deepening expertise in agentic RAG architectures, MLOps with Airflow and MLflow, and large-scale data processing with PySpark. Every project in this portfolio is built to a production standard: documented, deployed, and interactive — you can run the live demos directly above.
Open to ML engineering, data science, and applied AI roles. Feel free to reach out through any of the channels below.
Connect
