2026 - Intern AI Research Engineer - Networking & Inference Gateway

Location: Dublin, Ireland

Intern AI Research Engineer - Huawei Cloud Inference Serving Team

We are looking for an Intern AI Research Engineer to work on Huawei Cloud Inference Serving Team. Join us to push the boundaries of what's possible in Distributed AI inference performance and reliability. In this role, you won't be just writing code; you will be solving some of the most complex and exciting challenges in distributed Inference serving. Your work will directly impact the latency, efficiency, security and stability of our cloud-based AI services.

Responsibilities

• Develop and optimize core components of high-performance, low-latency AI inference gateway systems
• Implement request routing and load balancing mechanisms to efficiently distribute traffic across available resources
• Build networking optimizations and connection management systems to minimize latency and maximize throughput
• Create observability and monitoring tools for real-time performance analysis and system health tracking
• Develop REST and gRPC APIs that integrate seamlessly with existing ML infrastructure
• Write well-tested, maintainable code and participate in code reviews with the team

Requirements

• Currently pursuing BS/MS in Computer Science, Computer Engineering, or related field
• Strong programming fundamentals with experience in systems languages (Rust, Go, C++, or Java)
• Solid understanding of networking concepts including HTTP, TCP/IP, load balancing, and distributed systems
• Experience with concurrent programming, async patterns, and multi-threaded applications
• Knowledge of API development, web services, and service-oriented architectures
• Understanding of performance optimization techniques and system profiling

Nice to Have

• Strong candidates would understand transformer architectures and internals, and might have hands-on experience with model serving infrastructure, quantization techniques or building APIs around large language models
• Hands on experience with Rust programming language and its async ecosystem
• Familiarity with gRPC, Protocol Buffers, and high-performance RPC frameworks

What You'll Gain

This internship provides deep hands-on experience with modern systems programming and large-scale distributed networking infrastructure. You'll work closely with experienced engineers who will guide you through complex technical challenges in building production AI serving systems. The role offers valuable exposure to cutting-edge technologies like Rust async programming, high-performance networking, and observability systems, giving you skills that are highly valued across the industry. You'll contribute to real systems that handle production traffic while learning best practices in reliability, performance, and scalable system design.