Generative AI Engineer

This is us Kaltura (NYSE: KLTR) is a global software company on a mission to transform digital experiences from one-way interactions into intelligent, personalized conversations that move people forward. Founded in 2006, we started by making video more accessible to organizations around the world. Today, we're taking that foundation much further, combining conversational AI, rich media, enterprise knowledge, and data to build a new generation of intelligent digital experiences. Our technology helps organizations turn their content and knowledge into interactive, AI-powered experiences that can guide customers, train employees, support learners, and engage audiences in real time. From AI agents and personalized learning experiences to digital events, content hubs, and media platforms, we're changing how people interact with technology, and what technology can do for them. More than 1,000 organizations worldwide rely on Kaltura, reaching over 100 million users at home, at work, and at school. And the people behind it? We're a global team of 600+ employees, with offices in New York, London, Singapore, and Tel Aviv, united by a culture of openness, flexibility, and collaboration. Kaltura is a fast-paced environment where ideas are welcome, initiative is encouraged, and there's always something new to build, challenge, or improve. We believe in giving people the freedom to make an impact, the flexibility to balance work and life, and the opportunity to grow as we continue to evolve. The Role You are a hands-on engineer in an AI Professional Services (Forward-Deployed) Engineering pod — a small team embedded with priority enterprise customers, owning technical delivery from initial discovery and prototyping through to stable production. You build customer-specific capabilities that deliver immediate operational value and become durable platform primitives when proven broadly useful. Scope & What You Build Production Skills & Agents: understanding of microservices, AI applications and product Automated Evaluation Suites: Ground-truth test scenarios, golden datasets, and regression suites measuring semantic correctness, tool-call fidelity, and behavioral stability. Observability & Continuous Tuning: be familiar and up to date on observation and measuring techniques Requirements 2+ years in production software engineering: Deep hands-on experience building backend services, distributed systems, and APIs in Python , TypeScript/Node.js , or Go . You personally write, review, and ship production code. Production LLM & Agentic AI systems: Direct experience building and deploying stateful agent workflows, tool/function calling, structured outputs, context window optimization, and production RAG pipelines (hybrid search, semantic chunking, re-ranking). Customer-facing technical ownership: Proven experience acting as a technical lead with external engineering teams (Forward-Deployed Engineer, Solutions Engineer with production code ownership, or founding engineer). Design and Understand Architecture : Able to conduct architecture reviews and designing agentic systems Discovery under ambiguity: Ability to enter complex, unfamiliar enterprise environments, extract technical requirements from messy business problems, and rapidly design working systems. Strongly Preferred Model Context Protocol (MCP): Hands-on experience authoring or consuming MCP servers and clients to standardize agent tool interoperability. Speech pipelines: Background in ASR domain vocabulary biasing and TTS pronunciation tuning. Multi-tenant architecture: Experience enforcing strict tenant isolation and preventing cross-tenant context leakage.