Software Engineer (LLMOps)

Maisa AI is looking for a skilled Software Engineer to join our team and help build the infrastructure that makes enterprise AI reliable, scalable, and accessible. You will play a key role in optimizing our LLM serving capabilities and ensuring our platform meets the high demands of our enterprise customers.

Key responsibilities

• Build and optimize LLM serving infrastructure using technologies such as vLLM or SGLang.
• Manage GPU infrastructure, including orchestration, scaling, capacity planning, and high availability.
• Optimize inference performance and costs through batching, quantization, and GPU utilization improvements.
• Develop monitoring and observability tools for model serving to track latency, errors, and infrastructure health.
• Build and maintain CI/CD pipelines and infrastructure-as-code for automated, reliable model deployments.

Requirements

• Strong background in Infrastructure Engineering, Platform Engineering, or LLMOps with experience running ML workloads in production.
• Hands-on experience with LLM serving technologies and GPU infrastructure orchestration.
• Strong production experience with Kubernetes, Docker, Terraform, and CI/CD pipelines.
• Proficiency in Python and/or Go programming languages.
• Strong ownership mindset and ability to collaborate effectively across engineering teams.

What we offer

• Work on cutting-edge enterprise AI with real-world applications and major global customers.
• Solve complex engineering challenges involving GPU infrastructure and secure, high-performance deployments.
• Take ownership of the architecture, reliability, and cost-efficiency of our AI platform.
• Collaborate with a talented team in a fast-growing, ambitious company.