Senior Software Engineer (AI/LLM Systems)

<p class="ql-header-3" data-pm-slice="0 0 []"><strong>About PubNub</strong></p> <p class="editor-paragraph">PubNub is a San Francisco–based product company powering real-time experiences including chat, live updates, and interactive applications for 2,000+ companies including Verizon, Autodesk, Zillow, and Dropbox.</p> <p class="editor-paragraph">Our global data network processes trillions of messages each month with sub-100 ms latency across 15+ data centers worldwide.</p> <p class="editor-paragraph">We’re building an AI capability layer that helps developers add AI features to real-time streams such as classification, summarization, routing, enrichment, and automation, without breaking latency, reliability, or trust.</p> <p class="ql-header-3"><strong>What You’ll Do</strong></p> <p class="editor-paragraph"><strong>Ship AI-powered features into production</strong></p> <p class="editor-paragraph">Integrate LLM inference, build evaluation and observability tooling, and own the full lifecycle of AI services — from quality metrics and tracing to cost and reliability.You’ll work with providers like OpenAI, AWS Bedrock, Azure, or open-source models and deliver features used by real customers.</p> <p class="editor-paragraph"><strong>Build &amp; operate AI services at scale</strong></p> <p class="editor-paragraph">Design low-latency inference pipelines for high-throughput message streams.Implement model routing, prompt and retrieval patterns (RAG), caching, batching, and fallbacks.You’ll solve real-world constraints around latency, scale, and cost.</p> <p class="editor-paragraph"><strong>Enable other teams</strong></p> <p class="editor-paragraph">Build internal frameworks, APIs/SDKs, and tooling so other teams can ship AI features safely and consistently.Partner with product and engineering on trade-offs between latency, cost, accuracy, and privacy.Clear documentation and great developer experience matter here.</p> <p class="editor-paragraph"><strong>Tech &amp; Communication</strong></p> <p class="editor-paragraph">Work mainly with TypeScript, Python, or Rust (and be open to learning the others).Use modern AI-assisted tools (Copilot, Cursor, Claude, etc.).Communicate clearly in English.</p> <p class="ql-header-3"><strong>How we Work</strong></p> <ul> <li class="editor-paragraph">Long-term B2B collaboration (full-time engagement)</li> <li class="editor-paragraph">Competitive monthly compensation: 26,000 – 35,000 PLN + VAT</li> <li class="editor-paragraph">Remote-first within Poland</li> <li class="editor-paragraph">Flexible time management focused on outcomes</li> <li class="editor-paragraph">Access to modern tools and infrastructure required to perform the role effectively</li> <li class="editor-paragraph">Equity participation opportunity</li> <li class="editor-paragraph">Optional access to our centrally located Katowice office</li> </ul> <p class="editor-paragraph">If this sounds like the kind of systems challenge you enjoy, apply and include a short note about a production AI feature you’ve shipped.We review every application personally.</p>