Bliro: - The AI assistant for field sales - Takes desk work off sales reps' plates entirely, with more than one million customer touchpoints documented - Trusted by lighthouses of the German Mittelstand like igus, Lanxess and Brillux - Backed by 468 Capital, Lea Partners, Rockstart and more, with over €3M raised - See Bliro in action: https://bliro.io Why We're Hiring This Role: - Our chat agent and our voice to voice phone agent process and document thousands of customer interactions a week for field sales teams. Every answer has to be right, fast and useful on the road. - Our backend engineers build the platform. We need a senior AI engineer who owns agent quality: what the agents say, how well they say it, and how we prove they got better. - You'll own prompting and context, model benchmarking for our use cases, evals, and the agent harness behind both agents. You join a small team of high performing specialists who own the core of our agents. This role is about orchestrating and evaluating models, not training them. What You'll Do: - 30 Days: Map Bliro's chat and voice agents end to end. Partner with the backend engineers, review real user conversations, identify the biggest failure modes, and ship an initial improvement. - 60 Days: Own agent quality measurement. Build eval sets and metrics for our key use cases, benchmark models on quality, latency and cost, and ship a change with a measurable improvement against the baseline. - 90 Days: Establish a repeatable model for improving agent quality. Run evals on every prompt, model and harness change, turn real conversations into new test cases automatically, and set the longer term roadmap for agent quality. Who You Are: - Evidence of ownership and shipping LLM agents to real users and proving with data that they got better. You can demonstrate excellence and pursued a technical major at one of the major technical universities like TUM, ETH, KIT, RWTH, EPFL, etc. - Strong Python and the ability to debug agent behavior across prompts, tools, context and model choice. - Hands on experience building eval pipelines, LLM judges and model benchmarks, with enough statistics to tell a real gain from noise. - You ground your decisions in real user data, using AI to help analyze them, and turn what you find into test cases, fixes and clear priorities. - Deep curiosity and the ability to gather context quickly, form a clear point of view, and keep pace as models and the product evolve. - A low ego teammate who communicates clearly and owns outcomes. Familiarity with AI coding tools is expected; experience with the latest agent frameworks, realtime voice agents and multilingual agents is a plus. - This is a full time role. We prefer hybrid in Munich but are open to remote. How We Work: - Ambition: We get better every day by being curious and bold. - Continuous improvement: Move fast and break things, but never the same thing twice. - It's our problem: We operate as one team. We share credit, own mistakes together, and support each other when things get hard. - Why not today? We value urgency and momentum. The fastest path to customer value usually wins. - Build something worthy of love: Craft matters. We aim to build products customers genuinely love. Why Bliro: - Generational impact: Build the human interface for millions of field sellers - Ownership culture: Many of us are former founders - Forward thinkers: We are the world leader in privacy preserving transcription, we know how boundaries can be overcome What We Offer: - Real stake: Strong base salary plus meaningful equity ownership - Time off: 30 days of PTO, so take what you need - Hybrid setup: Work from our office in the heart of Munich, right next to the Frauenkirche, or from home. We value outcomes, not attendance - More: Free meals and drinks, Deutschlandticket, best in class equipment, and Wellpass