Senior Inference Engineer - AI Serving & Performance

Aleroy; Abu Dhabi; On-site; AED 550,000 - 850,000; Full time

Benefits offered by this job

Backend ownership

Architecture influence

Senior team with speed

Health insurance

Office in Yas Creative Hub

24 days annual leave

Competitive salary

Job summary

Aleroy is hiring a senior AI serving engineer to own and optimize the inference serving stack across GPU performance, MoE models, and quantization. You will lead benchmarking, instrumentation, and engineering standards, while guiding a small, senior team through hands-on implementation and problem solving.

The role focuses on building scalable, high-throughput serving systems for advanced AI workloads. You will set the technical roadmap, collaborate across teams, and maintain strong

Qualifications

• Hands-on experience building or operating LLM inference-serving systems in production.
• Deep understanding of inference stacks such as vLLM, SGLang, TensorRT-LLM, or similar technologies.
• Strong understanding of paged attention, continuous batching, disaggregated serving, KV-cache management, and modern inference architectures.
• Strong GPU performance engineering experience using CUDA or Triton.
• Experience serving large Mixture-of-Experts models, including expert parallelism and load balancing.
• Experience with model quantization and measuring quality against full-precision references.
• Strong benchmarking experience with latency percentiles and reproducibility.
• Ability to set technical direction while staying hands-on.

Responsibilities

• Own and improve the FAR Labs inference serving stack with disaggregation, batching, cache management, and routing optimisations.
• Improve throughput, latency, memory efficiency, and cost while maintaining model quality standards.
• Identify and eliminate GPU bottlenecks across the inference stack using CUDA, Triton, profiling, and memory optimisations.
• Drive efficient serving of MoE models including expert parallelism and distributed execution.
• Implement and evaluate quantization and other model optimisation techniques with accuracy checks.
• Own reproducible benchmarking across serving performance, quality, and cost.
• Build instrumentation to understand system behaviour and validate improvements.
• Make routing, scheduling, and caching decisions across diverse hardware environments.
• Define the AI serving and measurement roadmap and prioritise infra improvements.
• Establish clear technical standards around inference performance and testing.
• Mentor engineers across serving, metrics, and testing.

Skills

LLM inference-serving

GPU performance engineering

Distributed systems

Benchmarking & measurement

Technical leadership

Model quantization

MoE serving

Inference optimization

Tools

CUDA

Triton

vLLM

SGLang

TensorRT-LLM

Job description

Aleroy is hiring a senior AI serving engineer to own and optimize the inference serving stack across GPU performance, MoE models, and quantization. You will lead benchmarking, instrumentation, and engineering standards, while guiding a small, senior team through hands-on implementation and problem solving.

The role focuses on building scalable, high-throughput serving systems for advanced AI workloads. You will set the technical roadmap, collaborate across teams, and maintain strong