AI Infrastructure Engineer, Model Serving Platform

As a Software Engineer on the ML Infrastructure team, you will design and build platforms for scalable, reliable, and efficient serving of LLMs and AI agents. Our platform powers cutting-edge research and production systems, supporting both internal and external use cases across various environments.

The ideal candidate combines strong ML fundamentals with deep expertise in backend system design. You’ll work in a highly collaborative environment, bridging research and engineering to  deliver seamless experiences to our customers and accelerate innovation across the company.

You will:

• Build and maintain fault-tolerant, high-performance systems for serving LLMs and agent-based workloads at scale.
• Collaborate with researchers and engineers to integrate and optimize models for production and research use cases.
• Conduct architecture and design reviews to uphold best practices in system design and scalability.
• Develop monitoring and observability solutions to ensure system health and performance.
• Lead projects end-to-end, from requirements gathering to implementation, in a cross-functional environment. 

Ideally you'd have:

• 4+ years of experience building large-scale, high-performance backend systems.
• Strong programming skills in one or more languages (e.g., Python, Go, Rust, C++).
• Deep understanding of concurrency, memory management, networking, and distributed systems.
• Experience with containers, virtualization, and orchestration tools (e.g., Docker, Kubernetes).
• Familiarity with cloud infrastructure (AWS, GCP) and infrastructure as code (e.g., Terraform).
• Proven ability to solve complex problems and work independently in fast-moving environments.

Nice to haves:

• Experience with modern LLM serving frameworks such as vLLM, SGLang, TensorRT-LLM, or text-generation-inference.
• Knowledge of ML frameworks (e.g., PyTorch or TensorFlow) and how to optimize them for production serving.
• Experience with model inference optimizations such as quantization, distillation, speculative decoding, etc.
• Familiarity with emerging agent frameworks such as OpenHands, Agent2Agent, MCP.