ML Platform Engineer: Distributed LLM & Model Serving

Remotedxb; Dubai; On-site; AED 18,000 - 30,000; Full time

Job summary

Quora seeks a talented student graduate in 2025 or 2026 to join its engineering team in Dubai. You will build and maintain core infrastructure for the ML platform, ensuring scalability and high performance across distributed systems for LLMs and recommendations.

You will optimize GPU model serving for latency, throughput, and cost, collaborating with cross-functional teams while gaining exposure to cutting-edge ML tooling and cloud environments.

Qualifications

• Graduating in 2025 or 2026 in Computer Science, Engineering, or a related technical field.
• Proficiency in Python, Go, or C++.

Responsibilities

• Build and maintain core infrastructure for Quora's ML platform to ensure scalability and performance.
• Develop distributed systems for serving Large Language Models (LLM) and Recommendation Models
• Optimize GPU model serving for latency, throughput, and cost efficiency

Skills

Python

Go

C++

Education

Bachelors in CS/Engineering

Tools

Kubernetes

Docker

AWS

Job description

Quora seeks a talented student graduate in 2025 or 2026 to join its engineering team in Dubai. You will build and maintain core infrastructure for the ML platform, ensuring scalability and high performance across distributed systems for LLMs and recommendations.

You will optimize GPU model serving for latency, throughput, and cost, collaborating with cross-functional teams while gaining exposure to cutting-edge ML tooling and cloud environments.