Leul A.Private profile: Upwork shows its earnings only to signed-in members, so we check it every few weeks, not daily. MRR here is a rough estimate (Upwork's six-month earnings ÷ months active). Last read Nov 5, 2026.

Building an AI agent, RAG platform, or LLM product that must work reliably in production? I’m a Top Rated Plus AI/ML engineer with 100% Job Success, and 7+ years delivering production AI systems. I help startups and product teams move from idea or prototype to secure, testable, maintainable software. I can own the full lifecycle: architecture, data ingestion, retrieval, model integration, tool calling, evaluation, deployment, and observability. What I can deliver: • RAG and enterprise search with citations, hybrid retrieval, reranking, and vector databases • Tool-using AI agents and multi-agent workflows with structured outputs, guardrails, retries, and human approvals • Conversational AI for support, sales, coaching, research, and document-heavy workflows • Fine-tuned open-source LLMs using LoRA/PEFT, served with vLLM and production APIs • Python/FastAPI services, WebSockets, background workers, third-party integrations, and cloud deployment • LLM evaluation, prompt regression testing, monitoring, and latency/cost optimization Selected systems: • Agentic Analytics Platform — agentic advertising analytics and sales platform with role-gated tools, secure report ingestion, and grounded reports • Morpheus Agent — multi-agent crypto intelligence with structured orchestration and real-time data tools • Braino — insurance RAG assistant using a fine-tuned Llama model and vLLM serving • MAI Coach — digital coaching assistant combining OpenAI and a fine-tuned open-source Llama model • Auronity — multimodal analysis for manipulation, fact verification, contextual memory, and decision support Core stack: Python, FastAPI, OpenAI, Claude, Hugging Face, PyTorch, vLLM, Pinecone, FAISS, pgvector, PostgreSQL, Redis, Celery, Docker, CI/CD, AWS, Azure, and GCP. AWS Certified Machine Learning Engineer - Associate. Send me your use case, data sources, and current stack. I’ll respond with a practical path from idea to production.