Looking for an AI/ML Engineer who builds production-ready LLM systems? You're in the right place.
I’m a Machine Learning Engineer and graduate student at the University of Colorado Boulder focused on building scalable, high-performance AI systems. My work combines large language model engineering, multi-GPU inference optimization, AI agent development, and production deployment across cloud environments.
I’ve fine-tuned multilingual LLMs, architected low-latency pipelines, and implemented alignment techniques to improve model stability and output quality. I also design and integrate AI agents that interact with external tools, APIs, and retrieval systems to support real-world workflows. I’m currently contributing to an AI tutor project supporting students in Kenya, where I’m developing chatbot pipelines and implementing Retrieval-Augmented Generation to enable grounded, textbook aware responses.
I’m driven by building intelligent systems that are both technically efficient and practically impactful. I’m particularly interested in work that connects LLM systems, agents, retrieval pipelines, and scalable infrastructure into reliable production solutions.
⚙️ Tech Stack
💻 Programming Languages
Python | C++ | SQL | JavaScript
🧠 Machine Learning / AI Frameworks
PyTorch | TensorFlow | Scikit-learn | Hugging Face Transformers | Sentence Transformers | PEFT
⚡ Model Optimization & Inference
vLLM | DeepSpeed | Accelerate | Dynamo | QLoRA | Quantization | KV Cache Optimization | Multi-GPU Scheduling
☁️ LLM Retrieval & RAG
FAISS | ChromaDB | Pinecone | RAG
☁️ Cloud & MLOps
Google Cloud (Vertex AI, Cloud Run, GKE) · AWS (SageMaker, Lambda, S3, API Gateway, EC2) | Docker | Kubernetes | GitHub Actions |CI/CD
🤖 AI Agents & Orchestration
LangChain | LangGraph | FastMCP | MCP | A2A | Agent Pipelines | LLM Tool Integration
🗄️ Databases
MySQL | PostgreSQL | MongoDB
🧰 Backend / Web Development
Node.js | Django | FastAPI | Flask | React.js | REST APIs