Sefineh Tesfa

I am deeply inspired by Amazon’s Leadership Principles. Customer Obsession, Dive Deep, and Earn Trust standing out as my strongest values.

Contributions


About


AI Engineer specialized in small language model (SLM) development, Prompt engineering,  AI agent engineering, and Generative AI systems. I design and deploy production-grade AI solutions that combine compact, efficient models with advanced orchestration pipelines, delivering scalable and high-performing applications.
I focus on bridging the gap between cutting-edge AI research and real-world use cases—creating reliable, resource-efficient models and intelligent agents tailored for practical deployment.
🔹 Small Language Model Development
Build and optimize SLMs for efficiency and on-device deployment
Fine-tune compact models (LLaMA, Mistral, Hugging Face) for specialized tasks
Implement quantization, pruning, and distillation techniques for performance gains
Design evaluation tools and benchmarking workflows for SLM performance
🔹 AI Agent Engineering
Architect intelligent agents using LangChain, LlamaIndex, and Model Context Protocol (MCP)
Build Retrieval-Augmented Generation (RAG) pipelines with vector databases like Pinecone and FAISS
Integrate APIs, tools, and real-time data into autonomous agent workflows
Ensure secure, consistent, and verifiable agent actions in complex environments
🔹 Generative AI & Applied AI
Deploy generative systems for NLP, knowledge management, and decision support
Develop semantic search, embeddings, and reasoning pipelines
Optimize inference on GPU-powered and resource-constrained infrastructure
🔹 MLOps & Cloud AI
End-to-end model lifecycle: training, fine-tuning, deployment, and monitoring
Deliver cloud-native AI deployments on AWS (SageMaker, EC2, S3) and GCP AI services
Implement scalable vector search and semantic retrieval for enterprise-grade solutions
Passionate about advancing small language models and intelligent agents, I deliver future-ready AI systems that are efficient, secure, and impactful across industries.
Core Skills
✅ Small Language Model Development • Quantization • Distillation
✅ AI Agent Engineering (LangChain, LlamaIndex, MCP)
✅ Generative AI • RAG Pipelines • LLM Fine-Tuning
✅ Hugging Face Transformers • GPT • Claude • LLaMA • Mistral
✅ Vector Search (Pinecone, FAISS) • Semantic Embeddings
✅ GPU Inference • MLOps • Cloud AI (AWS SageMaker, GCP AI Services)
✅ NLP • AI Ethics • Performance Optimization

I am deeply inspired by Amazon’s Leadership Principles and how they drive innovation and collaboration. I strive to embody all 16 in my work, with Customer Obsession, Dive Deep, and Earn Trust standing out as my strongest values, guiding me to deliver impactful and reliable solutions.