Octavian Teodorescu

Solution architect with 18 years in enterprise technology, and for the last few years a hands-on builder of AI agents. I shape large transformation deals (usually $25-50M) for banking, insurance, energy, manufacturing and life-sciences clients, owning the design from operating model through to architecture and commercials. Alongside that I design, build and run agentic AI systems myself: multi-agent orchestration, MCP tool servers, retrieval pipelines, and a self-hosted agent runtime that runs in production on my own infrastructure. I also fine-tune small language models on a single local GPU, to understand the stack from the weights up rather than only from the slide deck. Most architects at my level stopped touching the keyboard years ago. I didn't.

• Agentic AI engineering: multi-agent systems, agent orchestration, MCP (Model Context Protocol) tool design, RAG and retrieval pipelines, prompt engineering, evals, LLM application design (Anthropic Claude and others)
• Applied ML, hands-on and growing: fine-tuning with LoRA and QLoRA, dataset curation, training and inference loops, model evaluation
• Enterprise solution architecture: large-deal shaping, reference architectures, operating and delivery model design, transition planning, commercial structuring
• Cloud and platform engineering: Azure, AWS, GCP, Kubernetes, Terraform, Ansible, CI/CD, IaC, Docker, self-hosting
• Service management heritage: ITSM, AMS, ServiceNow, SIAM, AIOps, intelligent ticket analysis

• Built and run a self-hosted multi-agent stack on my own NAS: a containerised agent runtime, a custom MCP server exposing 20+ tools, and a daily autonomous intelligence-brief agent with a multi-source ingest pipeline. Real production use, not a weekend prototype.
• Delivered production multi-agent solutions for enterprise clients on Copilot Studio and Power Automate, including an intelligent ticket-analysis system with an orchestrator and a data agent split across a strict data-handling boundary.
• Shaped enterprise transformation solutions across banking, insurance, energy, manufacturing, life sciences, and private equity, with deal values in the $25-50M range.
• Fine-tuned small language models end to end on a single RTX 4070 (QLoRA, axolotl, dataset curation to inference and adapter merge), to build genuine depth in the training stack.
• Cut infrastructure cost by around 25% and deployment time by roughly 70% on a cloud automation programme using IaC, CI/CD, and platform engineering.
• Led private cloud architecture for a major UK bank under strict regulatory and security constraints, reaching 99.9% uptime across a two-year on-site engagement.

Personal work, built and run on my own infrastructure. Where I keep my hands in the actual engineering.

• Self-hosted agent runtime: a containerised runtime on my NAS that hosts autonomous agents, fronted by TLS and auth, with a Telegram channel and scheduled jobs. I own it end to end: Docker, networking, reliability.
• Custom MCP server (second brain): an MCP server I wrote that exposes 20+ tools over my knowledge base (search, read and write, task capture, hygiene, tiered session-context priming), reachable over a Cloudflare tunnel and consumed by several agents and a web LLM connector. Where I learned context engineering and tool-calling design for real.
• Autonomous daily intelligence brief: an agent that ingests video transcripts, social posts, newsletters, news feeds and LLM passes, then tiers sources, detects convergence, gates on freshness, and routes work across cheaper and stronger models to keep cost sane. Effectively a small one-person AI product.
• Multi-agent reasoning pipelines: parallel reconnaissance agents for research, and a gated strategy pipeline that runs an adversarial critic against a hypothesis and labels each claim with a confidence level.
• Model fine-tuning: QLoRA fine-tuning of small language models on a single RTX 4070 in WSL using axolotl, dataset curation to JSONL, preprocessing, training, inference, adapter merge, and eval. Ongoing and deliberately hands-on.
• Self-improving tooling: a skill and agent library with usage telemetry and an automated review loop that flags what to improve.