Senior AI Engineer (LLM & Real-Time Systems)

About PubNub

PubNub powers real-time experiences for 2,000+ companies including Verizon, Autodesk, Zillow, and Dropbox.

Our global data network processes trillions of messages monthly with sub-100ms latency across 15+ data centers worldwide.

We’re now building an AI capability layer that enables developers to add AI features (classification, summarization, routing, enrichment, automation) directly into real-time streams — without compromising latency, reliability, or trust.

This is where you come in.

What You’ll Build

You’ll design and operate production AI services that integrate directly into PubNub’s real-time messaging platform.

This is a systems + platform engineering role with applied AI, not research.

You’ll work on:

• AI-powered moderation and enrichment pipelines

• Low-latency inference systems running on high-throughput streams

• Internal APIs, SDKs, and tooling that enable product teams to ship AI safely

• Observability, evaluation, drift detection, and production debugging workflows

• Model routing, retrieval patterns (RAG), batching, caching, fallbacks

• Trade-offs between latency, cost, accuracy, and privacy

You will not be training foundation models from scratch.

Must Have

• 5+ years backend / platform engineering experience

• 1+ year shipping AI-enabled features in production

• Experience integrating LLMs (OpenAI, Azure OpenAI, Bedrock, OSS models, etc.)

• Experience building high-throughput systems (streaming, queues, real-time APIs)

• Strong fundamentals in system design (performance, reliability, observability)

• Fluency in TypeScript, Python, or Rust(and willingness to work across ecosystems)

• Comfortable using AI-assisted development tools (Copilot, Cursor, Claude, etc.)

• Fluent English

Nice to Have

• Real-time systems (Kafka, Kinesis, WebSockets, pub/sub, event-driven design)

• Kubernetes / Docker / infra-as-code

• Model serving tools (vLLM, Triton, TensorRT, TorchServe)

• Vector search / embeddings / RAG pipelines

• Experience handling PII, compliance, safety guardrails in AI systems

Why This Role Is Interesting

• You’ll ship AI that runs in real time — not offline batch jobs

• You’ll solve hard constraints: latency, scale, cost, trust

• You’ll build internal platform primitives used across multiple teams

• You’ll work on greenfield AI systems with real production impact

Why PubNub

• Remote-first within Poland

• Optional office in central Katowice

• Competitive B2B compensation: 26 000 – 35 000 PLN net/month

• Work on real production AI at global scale

• Engineering-heavy culture (50%+ developers)

If you want to build AI that works under real-world scale constraints, not just demos, we’d love to talk.