Senior AI Platform Engineer (#5640

N-iX is a global software development company founded in 2002, connecting over 2,400+ tech professionals across 40+ countries. We deliver innovative technology solutions in cloud computing, data analytics, AI, embedded software, IoT , and more to global industry leaders and Fortune 500 companies. Join us to create technology that drives real change for businesses and people across the world.

Our client is a fast-growing European fintech company in the business spend management space — corporate cards and related financial products — serving SME and mid-sized business customers across the EU and UK, in a regulated environment with GDPR compliance obligations. Engineering is organized into cross-functional squads, with platform/enabling teams providing shared tooling horizontally. The client already runs an AI-native engineering practice:
Claude Code and Git Hub Copilot are used daily, supported by a growing library of shared, versioned Skills embedded in key repositories, enabling an end-to-end flow from ticket to implementation, testing and PR in several codebases. AI tool/connector rollout follows an approved-list and pilot process. The client is AWS-first overall; for data platform and analytics workloads it also runs GCP, with Big Query as the primary data warehouse.

Day-to-day coordination is Slack-first, with Linear for ticket tracking, Git Hub for code/PR review, and Notion as the knowledge base.

The client is also building out its AI platform and agentic capabilities: it recently launched an MCP surface in closed beta, giving external AI assistants a structured way to connect and perform real workflows behind guardrails, and treats agent reliability as a system property (tool contracts, approval/consent gates for write actions, evaluation harnesses).

We're looking for a Senior AI Platform Enginee
r to design, build and operate the shared GenAI infrastructure that product teams rely on.

Key Responsibilities:

• Design, build and operate shared GenAI infrastructure: LLM routing, vector search and RAG infrastructure, MCP gateway, and AI observability/evaluation tooling.
• Apply strong distributed-systems fundamentals: async workflows, idempotency, failure design.
• Work hands-on with LLM APIs in production.
• Apply an AI-security mindset: prompt injection defenses, PII-in-logs handling, credential handling.
• Apply real engineering rigor to the Context Development Lifecycle (CDLC): generate, evaluate, distribute and observe the context that powers AI agents.
• Multiply the output and quality of the squad you join, and share patterns/practice beyond your immediate team so adoption compounds across the organisation.
• Embed directly into a client squad as a hands-on Individual Contributor (not a coaching/managerial role).

Must-Have

Skills:

• Kotlin or Python as primary proficiency, with comfort contributing to both.
• Experience designing/building/operating shared GenAI infrastructure: LLM routing; vector search and RAG infrastructure; MCP gateway; AI observability and evaluation tooling.
• Strong distributed-systems fundamentals: async workflows, idempotency, failure design.
• Hands-on production experience with LLM APIs.
• AI-security mindset: prompt injection, PII in logs, credential handling.
• Agent & harness engineering fluency, with concrete evidence of building/operating this kind of tooling, not just using it.
• Comfortable with the client's current daily tools:
  Claude Code and Git Hub Copilot.

Nice-to-Have

Skills:

• Specific cloud depth (AWS and/or GCP), Grafana, or named LLM API vendors. The RFP describes these capabilities generically rather than naming specific tools for this role — listed here as plausible, not confirmed.