AI solution engineer for agentic platforms

We are seeking a Principal AI Solution Engineer to join an engineering organization building a sovereign, multi-tenant agentic AI platform, along with the applied products on top of it. Everything ships under strict data residency constraints and operates in both Arabic and English. Squads are small — three senior engineers — and decisions are made in the room. You will work across three layers and need to be credible in all of them: applied AI, AI infrastructure, and the backend platform.

• Set architecture for systems that span squads; write the decision down and defend it
• Build and tune GPU-based serving — vLLM, TGI or TensorRT-LLM — for latency, throughput and a cost per token you can justify
• Own the reference RAG and agent architecture other teams build against
• Define service boundaries, API contracts, event-driven infrastructure and the SLO work that prevents incidents rather than answering them
• Develop offline and online evaluation and regression detection, so models, prompts and retrieval can change without flying blind

• 5+ years of hands-on engineering experience with shipped production systems spanning applied AI, AI infrastructure and backend platforms
• At least 1 year of relevant leadership experience
• Expertise in Python and its production ecosystem, including FastAPI, Pydantic and asyncio
• Proficiency in production RAG end-to-end: ingestion, vector search, reranking and grounding evaluation
• Background in agent orchestration frameworks such as LangGraph, LangChain, OpenAI Agent SDK or Microsoft Agent Framework
• Competency in distributed systems, including idempotency, back-pressure and retry semantics, with strong event-driven architecture skills
• Knowledge of PostgreSQL at scale, along with GPU inference and serving using vLLM, TGI or TensorRT-LLM
• Familiarity with Kubernetes on Azure
• Skills in at least one infrastructure language: Go, Rust, Java or Kotlin
• Capability to use agentic coding tooling as a daily workflow, including project setup with CLAUDE.md, skills and agent configuration
• Excellent command of written and spoken English (B2+ level)
• Будет плюсом: Showcase of pgvector or Qdrant at production scale; Experience with Arabic-language, voice or conversational AI; Background in AI or mission-critical delivery in regulated environments such as government, defence or financial services; Familiarity with Azure sovereign cloud, Entra ID and Azure OpenAI; Understanding of Langfuse, Grafana, Prometheus and Terraform

• Условий в вакансии нет