Senior Backend Engineer (Go), LLM and RAG in production, AI product

We are New Wave Devs, a senior engineering team. We are hiring a Senior Go engineer to embed long-term with our client, a Netherlands-based AI-native creative-tools company building the backend of their AI Studio product.

It is a fast-paced product team: new frontier AI models are pushed into production within a day or two of release. You will own real pieces of the backend and work directly with their engineers.

What you will do:

• Design and scale Go microservices that manage the lifecycle of AI generations (image, video, audio, 3D, vector)
• Build and run RAG pipelines and agent orchestration around production models
• Handle long-running, resource-intensive inference tasks and high data throughput: queues, backpressure, retries
• Work with AWS (EKS, S3, Lambda), Kafka and SQS for async processing, ConnectRPC / gRPC / GraphQL
• Bridge AI model outputs into user-facing creative workflows

You should have:

• 5+ years backend, Go-first
• Hands-on LLM or RAG work that reached production, not API calls from a prototype: LangChain, LangGraph, pgvector or similar
• AWS (EKS/K8s), Kafka or SQS, gRPC/ConnectRPC, microservices at scale
• Ownership mindset, comfortable when specs are not perfect, able to switch between shipping fast and building for scale
• Real interest in the product itself. The client asks about it directly.
• Good English, daily work with the client team

We offer: long-term full-time contract through New Wave Devs, competitive rate, fully remote, fast start, days not weeks. Two technical interviews with the client's engineers, screen share and real code.