About PubNubPubNub powers the world’s most engaging real-time experiences—chat, live updates, and interactive applications—for over 2,000 companies including Verizon, Autodesk, Zillow, and Dropbox. Our global data network processes trillions of messages each month with sub-100 ms latency across 15+ data centers. Backed by $130M in funding, we’re shaping the future of how the world connects.About the RoleWe're looking for a Senior Software Engineer to build production AI features for Illuminate, our AI-powered decisioning and analytics platform. You'll architect systems that transform natural language into precise queries, detect anomalies in real-time data streams, and surface intelligent insights—all while operating at PubNub scale. This role requires equal depth in distributed systems, frontend development, and applied AI. You'll work asynchronously with team members across regions, with core overlap between 7am PT and 12pm PT. Responsibilities Design and build AI-powered features for the Illuminate analytics platformArchitect natural language to query systems that translate user intent into optimized SQLBuild React-based interfaces for AI-driven insights, anomaly detection, and query buildersDevelop low-latency pipelines processing analytical workloads across ClickHouse and PostgresCreate and maintain prompt architectures for complex multi-step AI workflowsBuild validation and error handling systems between LLM outputs and downstream data pipelinesIntegrate with Kafka/Kafka Streams for real-time data processing and AI inferenceCollaborate on system design with product and engineering teams across timezonesAbout YouMandatory Requirements Systems Engineering: Strong backend fundamentals with 5+ years experience in building high-throughput, distributed systemsProduction AI Experience: 1+ year shipping LLM-powered applications to customers (not just prototypes)Database Expertise: Strong SQL skills, particularly analytical patterns (aggregations, window functions, CTEs, query optimization)Frontend Skills: Solid React experience building complex, data-intensive UIsLLM Engineering:Experience with structured output extraction (function calling, JSON mode, tool use)Ability to design and iterate on prompt architectures for complex tasksUnderstanding of validation patterns between AI outputs and downstream systemsSystematic approach to testing non-deterministic systemsTech Stack: TypeScript, Kotlin, ReactCollaboration: Works effectively async across timezones; available 7am-12pm PT overlapAI-Assisted Development: Regular use of Copilot, Cursor, Claude, or similar toolsLanguage: Fluent EnglishNice to HaveExperience with MCP (Model Context Protocol)Background with columnar/analytical databases (ClickHouse, BigQuery, Snowflake)Kafka or Kafka Streams experienceQuery planning and optimization at the database levelExperience building evaluation datasets and regression test suites for LLM applicationsKnowledge of RAG patterns for schema/documentation retrievalExposure to semantic parsing or pre-LLM NL-to-SQL approachesUnderstanding of caching and performance optimization for LLM-based systemsDocker/Kubernetes experienceCloud AI platforms (AWS Bedrock, Azure OpenAI, Vertex AI)Prisma ORM experienceWhy Join PubNubBuild a greenfield intelligence platform at internet scaleShip features that land directly in customer-facing products across healthcare, fintech, gaming, and streamingAbout the RoleHigh ownership and influence over technical decisionsRemote-first setup within PolandCompetitive B2B compensation ranging between PLN26,000 - PLN32,000 per monthOptional office in central KatowiceIf you're excited to build AI systems that make complex data accessible and actionable, we'd love to hear from you.