Forward Deployed Engineer

<p class="p1">Sendbird is on a mission to build the AI workforce of tomorrow. Sendbird is the omnichannel AI agent platform enterprises choose to elevate the customer experience by initiating autonomous support sales conversations, keeping humans in the loop for complex inquiries, and re-engaging customers with proactive business messages. We are the omnichannel AI agent platform enterprises choose to elevate customer experience. Trusted by 4,000+ of the world’s most popular apps—including industry leaders like Match Group, Rakuten, Yahoo, and Coupang—Sendbird powers over 7 billion messages every month.</p> <p>We’re looking for a Forward Deployed Engineer (FDE) to contribute to Sendbird’s vision to connect businesses and individuals, empowering them to achieve more than ever before. As the FDE, you will play a critical role in building, integrating, and deploying production-grade AI agents tailored to each customer’s needs. You’ll operate at the front lines—engineering solutions alongside customers—while directly shaping the technical foundation of Sendbird’s AI Agent platform.</p> <p><strong>Who You Are</strong></p> <ul> <li>You have 2–3 years of hands-on software engineering experience, preferably in full-stack or backend development.</li> <li>You enjoy working directly with customers and thrive at the edge of engineering, product, and delivery.</li> <li>You love fast-paced environments, ambiguous challenges, and high-stakes problem solving.</li> <li>You think like an AI—mapping inputs to outcomes, reasoning through system prompts, and anticipating where things can go wrong.</li> <li>You understand Python, web frameworks, and LLM APIs—or you’re hungry to dive in and learn by building.</li> <li>You’re a team player who thrives in cross-functional collaboration with engineers, PMs, and designers.</li> </ul> <p><strong>What You Will Do</strong></p> <ul> <li>Collaborate with Forward Deployed PMs, core product teams, and designers to ship customer-centric solutions.</li> <li>Tune system prompts, configure toolchains, and iterate on agent behaviors to meet real-world use cases.</li> <li>Rapidly prototype and deploy AI agents using LLM APIs (e.g., OpenAI, Claude).</li> <li>Build and extend agent interfaces and dashboards using modern web frameworks like Next.js and React.</li> <li>Integrate backend APIs that power RAG pipelines, knowledge bases, and custom tools.</li> <li>Own the technical implementation for customer deployments—from setup to monitoring.</li> <li>Document implementation decisions, maintain architecture diagrams, and lead technical demos.</li> </ul> <p><strong>What You Bring</strong></p> <ul> <li>Strong proficiency in Python and ability to write clean, maintainable code.</li> <li>Hands-on experience with full-stack web development: React and modern JavaScript/TypeScript on the frontend, and backend frameworks such as Node.js, Django, or Express.</li> <li>Experience working with agent frameworks (e.g., LangChain) or LLM-based toolchains.</li> <li>Familiarity with retrieval-augmented generation (RAG) pipelines and knowledge base integration.</li> <li>Understanding of CI/CD practices and observability (e.g., logging, metrics dashboards, uptime monitoring).</li> <li>Experience deploying applications to modern cloud platforms (e.g., AWS Lambda, Vercel, GCP Cloud Functions).</li> <li>Strong collaboration skills and comfort working in agile, cross-functional teams.</li> <li>High ownership and comfort with ambiguity—you move fast, adapt quickly, and drive progress without waiting for perfect plans.</li> </ul> <p><strong>Added Value</strong></p> <ul> <li>Prior experience with real-time agent performance tuning or debugging live deployments</li> <li>Experience working in 0→1 environments, customer-facing implementation, or technical consulting roles.</li> </ul> <p><strong>What We Offer Includes (but is not limited to)</strong></p> <ul> <li>20 days PTO, 13 paid US company holidays, 7 sick days, 1 volunteer day, plus 2 rest/rej ... (truncated, view full listing at source)