AI Infrastructure Engineer: Scale & Serve Generative AI

Fireworks; San Mateo (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Fireworks is seeking a Software Engineer on the AI Infrastructure team to design core backend systems powering the company's generative AI platform. You will build scalable infrastructure for distributed training, inference, and data pipelines, partnering with product and cloud teams to deliver reliable, high-performance services.

The role emphasizes Python/Go development, ML tooling expertise, and hands-on CI/CD, model serving, and cost-efficiency.

Qualifications

• 3 years of software engineering experience with a focus on infrastructure or ML systems.

Responsibilities

• Contribute to the design and development of scalable backend infrastructure that supports distributed training, inference, and data pipelines
• Build and maintain core backend services such as LLM CI/CD pipeline, control plane, and model serving systems
• Support performance optimization, cost efficiency, and reliability improvements across compute, storage, and networking layers
• Building frameworks and safeguards to ensure Fireworks AI has the best model quality in the industry
• Collaborate with performance, training, and product teams to translate research and product needs into infrastructure solutions
• Participate in code reviews, technical discussions, and continuous integration and deployment processes

Skills

Python

Go

ML infra

Education

Bachelor's degree in CS/Engineering

Tools

PyTorch

MLflow

Kubernetes

Vertex AI

SageMaker

Job description

Fireworks is seeking a Software Engineer on the AI Infrastructure team to design core backend systems powering the company's generative AI platform. You will build scalable infrastructure for distributed training, inference, and data pipelines, partnering with product and cloud teams to deliver reliable, high-performance services.

The role emphasizes Python/Go development, ML tooling expertise, and hands-on CI/CD, model serving, and cost-efficiency.