Senior Agent Design Engineer

About the company

PolyAI is an enterprise conversational AI platform that deploys lifelike voice agents to manage complex customer interactions.

About this role

<div class="content-intro"><p>^{<span style="font-family: helvetica, arial, sans-serif;"><span><a href="https://poly.ai?utm_source=prnewswire&amp;utm_medium=pressrelease&amp;utm_campaign=boilerplate&amp;utm_content=pressrelease" target="_blank">PolyAI</a></span> is the Agentic Dialog Platform for building the conversational enterprise, used to build, run, govern, and improve dialog agents at scale. Powered by Raven, a proprietary dialog model trained on more than a billion enterprise conversations, PolyAI agents are built for complexity, open at every layer, and sovereign by design. PolyAI serves hundreds of enterprises across 75 languages and 25 countries, including Metro Bank, Marriott, PG&amp;E, and UniCredit.</span>}</p></div><p>^{<span style="font-family: helvetica, arial, sans-serif;">We're looking for a Senior Agent Design Engineer to lead the hardest agent work we take on, and to raise the bar for everyone building alongside them. This is a senior individual contributor role for someone who sits comfortably at the intersection of conversational UX design and technical implementation - someone who thinks critically about how conversations should feel, not just how systems should work.</span>}</p> <p>^{<span style="font-family: helvetica, arial, sans-serif;">At PolyAI, Agent Design means owning the full picture: mapping user journeys, shaping dialogue and tone, and building the underlying systems that power them - prompting, tool access, and context engineering. If you've spent your career frustrated by the artificial gap between design and engineering, this role was built for you.</span>}</p> <h2>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>What you'll do</strong></span>}</h2> <p>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Lead the hardest agent work.</strong> Our most complex, ambiguous, and high-risk initiatives - spanning multiple teams, markets, or strategic accounts - and get them live faster than anyone expects.</span>}</p> <p>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Build and own agentic workflows.</strong> Multi-agent loops, automated evaluation pipelines, autonomous tooling; designed and built end-to-end.</span>}</p> <p>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Set the quality bar.</strong> Reusable design approaches, evaluation methods, and measurement that improve outcomes well beyond your own projects.</span>}</p> <p>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Own client enablement.</strong> Run client and partner onboarding, and shape how the wider team enables customers to self-serve.</span>}</p> <p>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Raise the team and influence direction.</strong> Mentor Agent Designers at multiple levels, own an area of our Agent Design roadmap, and turn recurring delivery problems into priorities for Product and Engineering.</span>}</p> <h2>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>What we're looking for</strong></span>}</h2> <h3>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Required</strong></span>}</h3> <ul> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">5+ years in a technical or design adjacent role at a tech company, with genuine hands-on experience - whether you came from design and grew into technical depth, or from engineering and developed strong UX and language sensibility</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Python you can build in, not just read. You can build, test, debug, and deploy integrations yourself, and meaningfully review what others ship</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Demonstrable impact beyond your own projects: patterns other people adopted, an evaluation approach that spread past the work you built it for, colleagues who got materially better because of reviews you ran</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Familiarity with LLMs in practice: prompt engineering, tool use, retrieval, context management</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Hands-on experience building agentic systems - orchestration, tool-calling, multi-step workflows - and, just as importantly, evaluating them: automated evaluation pipelines and measurement of non-deterministic behaviour</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Experience owning external client relationships: challenging unclear requirements and explaining design decisions and trade-offs directly to customers</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Meticulous attention to language, tone, consistency, and interaction quality - with the judgement to know when to resolve ambiguity and when to ship anyway</span>}</li> </ul> <h3>^{<span style="font-family: helvetica, arial, sans-serif;"><strong>Preferred</strong></span>}</h3> <ul> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;">^{<span style="font-family: helvetica, arial, sans-serif;">Voice-specific craft: designing around latency, barge-in, ASR errors, and recovery</span>}</li> <li style="font-family: helvetica, arial, sans-serif; font-size: 12pt;"><sup><span st