AI Platform & LLM Infra Engineer

iSystems Ltd; Dubai; On-site; AED 279,000 - 502,000; Full time

Job summary

iSystems Ltd seeks a skilled specialist to optimize and maintain AI inference infrastructure. You will debug LLM serving, parser issues, and tool calls, while ensuring robust observability and scalable deployments.

Role emphasizes hands-on work with Docker/Kubernetes, API gateways, and performance tuning across GPU-accelerated environments in the UAE. Collaboration with cross-functional teams is essential.

Qualifications

• Hands-on experience with large language model inference serving and debugging.
• Strong troubleshooting for AI tooling, parsers and function calling.
• Practical knowledge of observability tools and distributed tracing.
• Experience with containerized production operations and API gateways.
• Familiarity with load, performance and capacity planning for AI workloads.

Skills

LLM inference

Harmony parser

Function calling

Context parsing

Output parsing

KV-cache

GPU monitoring

Tensor parallelism

Concurrency optimization

Batching optimization

Python debugging

API gateway

HTTP troubleshooting

TLS debugging

Load balancer

OpenTelemetry

Kibana

Request tracing

Retry logic

Graceful degradation

Load testing

Stress testing

Soak testing

Latency analysis

Capacity planning

Incident management

CI/CD

Rollback strategy

Tools

Docker

Kubernetes

Job description

iSystems Ltd seeks a skilled specialist to optimize and maintain AI inference infrastructure. You will debug LLM serving, parser issues, and tool calls, while ensuring robust observability and scalable deployments.

Role emphasizes hands-on work with Docker/Kubernetes, API gateways, and performance tuning across GPU-accelerated environments in the UAE. Collaboration with cross-functional teams is essential.