AI Platform Engineer

About the role

QNB is growing its AI organization and is looking for an AI Platform Engineer who can run AI systems in production and build the platforms behind them. Working alongside AI Engineers, you will take the agents they design to production on the bank's own GPU infrastructure, and build the platforms that let technical and non-technical users create, test and manage agents. Everything is built in-house.

Key responsibilities

• Take LLM-based agents from prototype to production: deployment, scaling, versioning, autoscaling, zero-downtime rollout and rollback, and disaster recovery.
• Deploy and optimize self-hosted LLM inference (e.g. vLLM) on GPU infrastructure on OpenShift/Kubernetes, including capacity planning, GPU utilization, batching, quantization and multi-model and LoRA serving.
• Load, stress and soak test agentic systems end to end, measure throughput, TTFT and inter-token latency, find bottlenecks and turn results into capacity plans.
• Build observability: structured logging, metrics, distributed tracing and LLM-specific telemetry such as token usage, cost and agent/tool-call traces.
• Write resilient applications with timeouts, retries, circuit breakers and graceful degradation, and apply security and compliance for a regulated, on-prem environment (authentication, secrets management, network isolation, audit logging, PII handling).
• Build the agent platform: agent builders, simulation and testing environments, MCP server and connector registries, prompt and version management, deployment and monitoring.
• Build the agent runtime: orchestration loop, tool calling and MCP integration, context, memory and state management, guardrails and sandboxed execution of untrusted code.
• Provide low-code interfaces for business teams and SDKs, APIs and CLIs for engineers, then gather feedback, shape the roadmap, drive adoption and train users.

Required profile

• Bachelor's degree in Computer Engineering, Software Engineering or a related field.
• At least 4 years in software, backend, platform, SRE or ML infrastructure engineering, with high-criticality, 24/7 services kept running.
• Strong Python and solid engineering practices (testing, code review, clean architecture); Go is a plus.
• Fluent English, awareness of security, data privacy and compliance in regulated environments, and an ownership mindset.

Required skills

• Kubernetes and/or OpenShift, including Helm/Operators, resource management and GPU scheduling (e.g. NVIDIA GPU Operator, MIG)
• Experience serving LLMs with vLLM or similar engines (TGI, SGLang, Triton, KServe)
• Performance testing (k6, Locust), LLM benchmarking (GuideLLM, LLMPerf) and observability tooling (Prometheus, Grafana, OpenTelemetry, ELK/Loki, Jaeger/Tempo)
• REST/gRPC APIs, async programming, microservices, Kafka; SQL with PostgreSQL and Redis
• Working knowledge of agent frameworks (LangChain, LangGraph), RAG, vector databases and MCP

A plus: low-code agent platforms (Langflow, Dify, n8n) or React, on-prem or air-gapped AI workloads, GitOps (ArgoCD, Tekton), chaos engineering, GPU capacity planning and fine-tuning pipelines (LoRA) through to serving.