Software Engineer - AI Agents & Platform

Software Engineer - AI Agents & Platform ABOUT ASSEMBLED Great customer support requires human agents and AI in perfect balance, and Assembled https://www.assembled.com/customers is the only unified platform that orchestrates both at scale. Companies like Canva, Etsy, and Robinhood use Assembled to coordinate their entire support operation — in-house agents, BPOs, and AI — in a single operating system. With AI Agents that resolve cases end-to-end, AI Copilot for agent assistance, and AI-powered workforce management that optimizes both human and AI capacity, Assembled helps teams deliver faster, better service while making smarter decisions about how to staff and automate. Backed by $70M from NEA, Emergence Capital, and Stripe, we're building the platform that makes AI and human collaboration actually work. THE TEAM Our AI Agents & Platform Team is building autonomous AI agents that handle the most challenging aspects of customer support and let human agents focus on high-value interactions. We're already deploying our systems at leading tech companies like Canva, Patreon, and Babylist, giving us complex real-world scenarios to solve with rapid feedback loops. The engineering challenges are significant: building autonomous agents that can reliably handle customer interactions, designing systems that scale across communication channels, and pushing the boundaries of what's possible with current LLM technology. Examples of what you might work on: - Scaling LLMs with Golang https://www.assembled.com/blog/scaling-llms-with-golang-how-we-serve-millions-of-llm-requests - Enhancing RAG results with Reciprocal Rank Fusion and Hybrid Search https://www.assembled.com/blog/better-rag-results-with-reciprocal-rank-fusion-and-hybrid-search - Pioneering new LLM evaluation techniques https://www.assembled.com/blog/ai-at-assembled-an-empirical-comparison-of-llm-evaluation-metrics-in-a-customer-support-setting RESPONSIBILITIES As a Software Engineer on the AI Agents & Platform Team, you will: - Build foundational new features: Develop product features from the ground up, such as implementing translation capabilities powered by LLMs and intelligent categorization of incoming tickets. You’ll help design and build a workflow builder that distills the complexity of workflows into a simple, intuitive interface, making powerful tools accessible and easy to use for support agents. - Improve LLM model results: Enhance our retrieval augmented generation engine using techniques like vector search, document re-ranking, and hypothetical document embeddings. You’ll help us leverage implicit knowledge bases like past tickets and macros to improve model performance. - Develop LLM Infrastructure: Architect the abstractions that enable the integration of various types of LLMs tailored for different applications. You’ll design and implement evaluation and logging systems to monitor performance and build interfaces that expand our platform's capabilities. - Engage with customers: Collaborate with our customers (both support agents and managers) to understand their needs, how they interact with our product, and how we can improve their lives. - Wear many hats: Be versatile in roles — coding, user research, planning, brainstorming, interviewing, and cross-team collaboration. - Shape the team culture: Encourage a startup mentality that’s all about staying positive, aiming for top-notch product quality, and taking initiative. ABOUT YOU You might be a good fit if you: - Have 5+ years of experience in software engineering as an individual contributor. - Are highly ambitious and driven and set high goals for yourself and others. - Put customers first, focusing on real problem-solving and making life easier for support agents. - Enjoy fast-paced environments and can quickly adjust when new insights come from customers or prospects. - Have a bit of a maverick streak that helps you come up with creative solutions for tough problems. - Have made a no ... (truncated, view full listing at source)