AI Engineer, Agent Analytics & Optimization (DPI) at Conviva

<div class="content-intro"><p><strong>Conviva is the experience analytics platform for AI agents, apps, and streaming. Conviva pioneered quality of experience measurement for streaming video and has supported live digital experiences across 20 Super Bowls, 10 Olympic Games, and five FIFA World Cup tournaments. With full-census, real-time, stateful analytics, Conviva shows what consumers actually experience, not just whether systems are running, and connects that experience to revenue, retention, and risk.</strong></p></div><p><span class="TextRun SCXW150468841 BCX0" lang="EN-US" data-contrast="auto"><span class="NormalTextRun SCXW150468841 BCX0">Conviva is the intelligence layer for digital businesses, turning every consumer interaction i</span><span class="NormalTextRun ContextualSpellingAndGrammarErrorV2Themed SCXW150468841 BCX0">nto ou</span><span class="NormalTextRun SCXW150468841 BCX0">tcome-based intelligence—linking </span><span class="NormalTextRun SCXW150468841 BCX0">engagement</span> <span class="NormalTextRun SCXW150468841 BCX0">patterns across AI agents, apps, websites, and streaming video to </span><span class="NormalTextRun SCXW150468841 BCX0">real results</span><span class="NormalTextRun SCXW150468841 BCX0"> such as purchases, bookings, and resolved support requests. Powered by its patented Time-State Technology®, the Conviva® Operational Data Platform delivers real-time insights and automation that help leading enterprises grow, improve satisfaction, and build lasting trust.</span></span><span class="EOP SCXW150468841 BCX0" data-ccp-props="{}">&nbsp;</span></p> <p>&nbsp;</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold"><strong>The Opportunity</strong></p> <p class="font-claude-response-body break-words whitespace-normal">AI agents are becoming a new digital surface alongside mobile and web. This role builds the systems that let AI agents understand, query, and act on Conviva's behavioral data — MCP servers, agentic workflows, and the AI connectors that tie the platform into any client or downstream system.</p> <p class="font-claude-response-body break-words whitespace-normal">This is a builder role end-to-end: design and ship agentic systems from tool interface through deployment, observability, and iteration — working closely with product and customers. This is not a research role, and it is not prompt engineering; the team builds production systems that use AI to solve real problems at scale.</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold">&nbsp;</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold"><strong>How This Role Fits</strong></p> <p class="font-claude-response-body break-words whitespace-normal">This is an <strong>engineering</strong> role, distinct from Conviva's Product Builder roles on the same team:</p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p><strong>Product Builders</strong> validate direction through customer discovery and prototypes — deciding <em>what</em> agent analytics should become.</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p><strong>This role</strong> turns that direction into production-grade systems that run reliably at scale — owning the build and the runtime, not the roadmap.</p> </li> </ul> <p class="text-text-100 mt-2 -mb-1 text-base font-bold">&nbsp;</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold"><strong>What Success Will Look Like:</strong>&nbsp;</p> <p class="font-claude-response-body break-words whitespace-normal">Build &amp; Ship</p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Design and build MCP servers that expose Conviva's data and analytics as discoverable, reliable tools for AI agents, with proper auth, scoping, and access controls</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Architect and ship agentic workflows: multi-step reasoning, tool use, orchestration patterns, and human-in-the-loop where needed</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Develop AI connectors integrating Conviva's intelligence with external agents, clients, and downstream systems</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Own the full lifecycle — API/tool design, deployment, monitoring, production hardening</p> </li> </ul> <p class="font-claude-response-body break-words whitespace-normal">&nbsp;</p> <p class="font-claude-response-body break-words whitespace-normal">Reliability &amp; Iteration</p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Use evals to validate agent behavior before shipping, catch regressions, and debug production divergence</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Build observability and tracing to make agent behavior inspectable and auditable</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Tune for latency, cost, and reliability as models and data drift</p> </li> </ul> <p class="font-claude-response-body break-words whitespace-normal">&nbsp;</p> <p class="font-claude-response-body break-words whitespace-normal">Execution &amp; Collaboration</p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Partner with Product Builders, design, and customers to ship working software (not prototypes)</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Build internal SDKs, reusable patterns, and shared context that raise the floor for the whole team</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Stay close to the fast-moving MCP/agent ecosystem and bring back what's relevant</p> </li> </ul> <p class="text-text-100 mt-2 -mb-1 text-base font-bold">&nbsp;</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold"><strong>Who You Are and What You've Done:</strong>&nbsp;</p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>3–7+ years of software engineering experience, with production systems shipped end-to-end</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Strong Python backend fundamentals; comfortable owning services from design through deployment (fullstack a plus)</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Hands-on experience building and operating LLM-powered agents in production — with concrete stories of what broke, how you fixed it, and what you'd do differently</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Practical familiarity with agentic patterns: tool use, structured outputs, prompt chaining, multi-agent coordination, and knowing when a deterministic workflow is the right call</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Experience designing/building MCP servers or equivalent tool-use / AI connector integrations</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Have used evals to validate and debug agent behavior</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Comfortable with cloud deployment (GCP/AWS), containerized services, and async Python</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Strong product instinct — thinks about what users actually need and pushes back when a spec doesn't add up</p> </li> </ul> <p class="text-text-100 mt-2 -mb-1 text-base font-bold">&nbsp;</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold"><strong>Bonus Points</strong></p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Experience with agentic frameworks (LangGraph, Anthropic SDK, Pydantic-AI, CrewAI, or similar)</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Agent observability/tracing (Langfuse, LangSmith, OpenTelemetry, or homegrown)</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Background in digital experience analytics, observability, or APM</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Familiarity with agent evaluation or LLM-ops tooling</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Published writing, talks, or open-source work at the intersection of engineering and AI</p> </li> </ul> <p class="text-text-100 mt-2 -mb-1 text-base font-bold">&nbsp;</p> <p class="text-text-100 mt-2 -mb-1 text-base font-bold"><strong>What We Offer</strong></p> <ul class="[li_&amp;]:mb-0 [li_&amp;]:mt-1 [li_&amp;]:gap-1 [&amp;:not(:last-child)_ul]:pb-1 [&amp;:not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3"> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>A front-row seat to a category being created in real time — agent analytics is where web analytics was in 2005</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>A team that values builders — we use AI every day to move faster, not just talk about it</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>A hybrid role shaping both the "what" and the "how" — strategy meets craft</p> </li> <li class="font-claude-response-body whitespace-normal break-words pl-2"> <p>Competitive compensation, equity, and benefits</p> </li> </ul> <p class="font-claude-response-body break-words whitespace-normal">&nbsp;</p> <p class="font-claude-response-body break-words whitespace-normal"><em>The expected salary range for this full-time position is $180<span class="katex"><span class="katex-mathml">,000–$250,000</span></span>&nbsp;+ equity + benefits. Actual level and compensation are determined by qualifications, professional background, and relevant experience.</em></p> <p>&nbsp;</p><div class="content-conclusion"><p><strong>Learn more at</strong> <u><span><a href="http://conviva.ai" target="_blank">conviva.ai</a></span></u> <strong>and follow the company on</strong> <u><span><a href="https://linkedin.com/company/conviva" target="_blank">LinkedIn</a></span></u> <strong>and</strong> <u><span><a href="https://www.youtube.com/@conviva-ai" target="_blank">YouTube</a></span></u>.</p></div>