Teams at Bliro

Own the quality of Bliro’s chat and voice AI agents by improving prompts, context, model selection, evaluation harnesses, and benchmarking. Review real conversations, identify failure modes, build test sets and metrics, measure quality, latency, and cost, and establish a repeatable process for continuous agent improvement. The role requires strong Python skills, experience shipping LLM agents, statistical evaluation expertise, and the ability to translate conversations into actionable fixes.

Lead outbound prospecting into the US market from Munich: research, cold-call, qualify leads, book demos, manage pipeline, and collaborate with founders and AEs to shape US positioning and support a US leadership visit.