Senior Software Engineer, Inference Platform

Who you are

You have 5+ years of software engineering experience, particularly in building scalable systems that support high-performance applications. Your background includes working with cloud-native technologies and you understand the intricacies of real-time data processing. You are comfortable collaborating with cross-functional teams, including AI researchers and engineers, to bring innovative solutions to life.

Your expertise in Java is complemented by a solid understanding of databases, particularly MongoDB. You have experience in designing and implementing systems that require low-latency responses and high reliability. You are passionate about performance optimization and have a keen eye for improving resource efficiency in cloud environments.

You thrive in collaborative settings and enjoy working with diverse teams to tackle complex challenges. Your communication skills allow you to articulate technical concepts clearly to both technical and non-technical stakeholders. You are proactive in seeking out opportunities for improvement and innovation within your projects.

Desirable

Experience with machine learning frameworks and concepts is a plus, as you will be working closely with AI engineers. Familiarity with observability tools and performance monitoring techniques will help you excel in this role. You are also open to learning new technologies and methodologies that can enhance your contributions to the team.

What you'll do

In this role, you will design and build components of a multi-tenant inference platform that integrates seamlessly with MongoDB Atlas. Your focus will be on supporting semantic search and hybrid retrieval capabilities, ensuring that the platform meets the demands of real-time applications. You will collaborate with AI engineers to productionize inference for embedding models, enabling both batch and real-time use cases.

You will contribute to enhancing platform capabilities such as latency-aware routing, model versioning, health monitoring, and observability. Your work will involve improving performance, autoscaling, and GPU utilization to ensure that the platform operates efficiently in a cloud-native environment. You will also work across product, infrastructure, and ML teams to ensure that the inference platform meets the scale, reliability, and latency demands of modern applications.

What we offer

MongoDB provides a competitive salary range for this role, with a base salary between $118,000 and $231,000 USD. You will have access to a comprehensive benefits package that includes health benefits, parental leave, and mental health counseling. We foster a culture of collaboration and innovation, encouraging you to bring your ideas to the table and contribute to the success of our products. Join us in building the future of data infrastructure and AI-native experiences.