{"spec":"human.json/0.5","handle":"hamza","name":"Hamza Tahir","headline":"Founder of ZenML. AI engineer working on agents and ML in production.","photo":"https://github.com/htahir1.png","location":{"city":"Munich","country":"DE","utc_offset":1},"status":"open","updated":"2026-10-21","summary":"I'm the founder of ZenML, an open-source AI platform that takes teams from ML pipelines to agents. What I think about most is getting agents and ML systems to work in production: evals, orchestration, and what breaks once real users arrive. If you're working on the same problems, I'd like to hear about them.","links":[{"label":"GitHub","url":"https://github.com/htahir1"},{"label":"ZenML","url":"https://zenml.io"},{"label":"ZenML on GitHub","url":"https://github.com/zenml-io/zenml"},{"label":"Practical AI: Building Durable AI Agents","url":"https://pocketcasts.com/podcast/practical-ai/f5413aa0-606d-0136-4e65-69745d675bc7/building-durable-ai-agents/44509097-c42f-4135-851a-672478419391"}],"languages":[{"tag":"en"},{"tag":"ur"},{"tag":"pa"},{"tag":"de"}],"identities":[{"label":"GitHub","url":"https://github.com/htahir1"}],"open_to":[{"type":"intro","status":"open","topics":["agents in production","evals","ML in production","LLMOps","MLOps"],"notes":"Conversations with people working on agents in production, evals, or machine learning in production. Bring a real problem you're working on."}],"not_open_to":["sales","marketing","recruiting_agency"],"projects":[{"id":"zenml","title":"ZenML","role":"Founder","summary":"One AI platform from pipelines to agents. Open source, Python.","outcome":"5,600+ GitHub stars and 665 forks (October 2026).","stack":["Python","MLOps","LLMOps","Agents"],"link":"https://github.com/zenml-io/zenml","source":"github"},{"id":"kitaru","title":"Kitaru","year":2026,"role":"ZenML project","summary":"Agent traces you can run, not just read: durable execution, checkpoints and replay for AI agents.","outcome":"310 GitHub stars in its first months.","stack":["Python","Agents","MCP"],"link":"https://github.com/zenml-io/kitaru","source":"github"},{"id":"mcp-zenml","title":"ZenML MCP server","year":2025,"role":"ZenML project","summary":"Connects MCP clients like Claude Desktop and Cursor to ZenML pipelines.","stack":["Python","MCP","LLMOps"],"link":"https://github.com/zenml-io/mcp-zenml","source":"github"},{"id":"zenml-document-processing-llms","title":"Document processing with LLMs on ZenML","year":2025,"summary":"An example of LLM document-processing pipelines, built on ZenML.","stack":["Python","LLMs"],"link":"https://github.com/htahir1/zenml-document-processing-llms","source":"github"},{"id":"cdtm-mcp","title":"cdtm-mcp","year":2026,"summary":"An MCP server for the CDTM Community Portal: search CDTM students and alumni from Claude in plain language.","stack":["Python","MCP"],"link":"https://github.com/htahir1/cdtm-mcp","source":"github"},{"id":"talk-practical-ai-durable-agents","title":"Building Durable AI Agents (Practical AI podcast)","year":2026,"role":"Guest","summary":"How to move agents from demos to reliable production systems: harnesses, checkpointing, retries, replay, and where Kitaru fits.","stack":["Agents","LLMOps"],"link":"https://pocketcasts.com/podcast/practical-ai/f5413aa0-606d-0136-4e65-69745d675bc7/building-durable-ai-agents/44509097-c42f-4135-851a-672478419391","source":"self"},{"id":"talk-mlops-community-while-loops","title":"Agents are Just While Loops (MLOps.community podcast)","year":2026,"role":"Guest","summary":"An agent is a while loop that talks to a model, calls a tool and writes to a file system. What durable execution does and does not guarantee.","stack":["Agents"],"link":"https://podbay.fm/p/mlopscommunity/e/1778855400","source":"self"},{"id":"talk-mlops-london-2026","title":"Local Code, K8s Scale: Building a Vendor-Agnostic AI Platform","year":2026,"role":"Speaker, MLOps Community London","summary":"The architecture of ZenML: how one framework bridges local development and production on Kubernetes.","stack":["MLOps","Kubernetes"],"link":"https://luma.com/5jivnk6l","source":"self"},{"id":"talk-future-of-data-ai-2023","title":"Navigating the MLOps landscape (panel)","year":2023,"role":"Panelist, Future of Data & AI Conference","summary":"Panel on running ML in production: best practices, implementation challenges and MLOps trends.","stack":["MLOps"],"link":"https://datasciencedojo.com/session/navigating-the-mlops-landscape/","source":"self"},{"id":"llm-bootcamp-instructor","title":"LLM Bootcamp (Data Science Dojo)","role":"Instructor","summary":"Taught part of Data Science Dojo's LLM Bootcamp.","stack":["LLMs","LLMOps"],"link":"https://datasciencedojo.com/instructor/hamza-tahir/","source":"self"},{"id":"pipeline-conversations","title":"Pipeline Conversations","year":2021,"role":"Co-host","summary":"ZenML's podcast on ML in production. I co-hosted six episodes, including an interview with Ines Montani of spaCy.","stack":["MLOps"],"link":"https://podcast.zenml.io/hosts/hamzatahir","source":"self"},{"id":"how-ai-built-this-72","title":"How AI Built This #72 (Fuzzy Labs podcast)","year":2022,"role":"Guest","summary":"Indie hacking, and running an MLOps startup in Germany.","stack":["MLOps"],"link":"https://www.fuzzylabs.ai/blog-post/how-ai-built-this-72-hamza-tahir","source":"self"},{"id":"bentoml-ama","title":"AMA with the BentoML community","year":2022,"role":"Guest","summary":"Community AMA about ZenML and MLOps.","stack":["MLOps"],"link":"https://www.bentoml.com/blog/ama-with-hamza","source":"self"}],"experience":[{"org":"ZenML","title":"Co-founder & CTO","from":"2021","to":"now","summary":"I co-founded ZenML and lead its engineering: the open-source framework, the MCP server and Kitaru for durable agents."},{"org":"maiot","title":"Co-founder & CTO","summary":"Deployed ML in production for predictive-maintenance use cases. ZenML grew out of what we learned there."},{"org":"Motius","title":"Machine Learning Engineer"},{"org":"Digital Product School","title":"AI Engineer"}],"faq":[{"q":"What do you want to talk about?","a":"Agents in production, evals, and machine learning in production. The more concrete the problem, the better.","tags":["topics","agents","evals","mlops"]},{"q":"What is ZenML?","a":"One AI platform from pipelines to agents. It's open source: github.com/zenml-io/zenml.","tags":["zenml","company"]},{"q":"Can I pitch you a product or a marketing service?","a":"No. I'm not open to sales or marketing pitches.","tags":["sales","marketing","pitch"]},{"q":"Where have you spoken before?","a":"Most recently on Practical AI (Building Durable AI Agents) and the MLOps.community podcast (Agents are Just While Loops), and at MLOps Community London on building a vendor-agnostic AI platform. Before that: an MLOps panel at the Future of Data & AI Conference, Data Science Dojo's LLM Bootcamp, and ZenML's own podcast, Pipeline Conversations.","tags":["talks","speaking","podcasts"]},{"q":"What did you do before ZenML?","a":"I co-founded maiot, where we put ML into production for predictive maintenance. ZenML came out of that. Before that I was an ML engineer at Motius and an AI engineer at Digital Product School.","tags":["background","career"]}],"agent_policy":{"auto_decline":true,"intro_requires":["written_jd"],"escalate":[],"contact":{"method":"url","url":"https://github.com/htahir1"},"notes":"This is Hamza's own file, used as the main example on this site. The other example people on this site are made up.","feedback":{"url":"https://humanjson.org/api/feedback/hamza"}},"skills":[{"name":"MLOps","level":5,"years":6,"evidence":["zenml","talk-mlops-london-2026","talk-future-of-data-ai-2023"]},{"name":"Python","level":5,"years":10,"evidence":["zenml","cdtm-mcp"]},{"name":"LLMOps","level":4,"years":3,"evidence":["zenml","mcp-zenml","llm-bootcamp-instructor"]},{"name":"Agents","level":4,"years":2,"evidence":["kitaru","zenml","talk-practical-ai-durable-agents"]},{"name":"MCP","level":3,"years":1,"evidence":["mcp-zenml","cdtm-mcp"]}]}