Streamline the deployment of Machine Learning models
As a Senior Developer on the Machine Learning team, you’ll play a key role in supporting other ML teams with the deployment and integration of ML models, including Large Language Models (LLMs), into existing infrastructure. Our team has built a mission-critical platform that trains thousands of models and serves over 100M model queries daily. This is your chance to accelerate AI innovation at Coveo by enhancing our ML platform’s capabilities to safely deploy, serve, and test models at scale.
As part of this team, you will develop, optimize and implement automated processes that facilitate model deployment, while ensuring scalability, reliability and performance. Are you driven by the challenge of expanding the capabilities of our machine learning platform? Then this is the opportunity for you!
Here’s what you’ll be responsible for:
- Contribute to every stage of the development lifecycle, from design and coding to automated testing and deployment.
- Design and implement scalable solutions to enhance operational efficiency and streamline automated deployments.
- Investigate and improve the performance, scalability, and efficiency of our platform infrastructure.
- Ensure high availability and reliability of services handling millions of requests per day.
- Contribute to the architecture and evolution of our platform by bringing forward innovative ideas.
- Collaborate with applied scientists, data engineers, and software developers to integrate models seamlessly into the existing infrastructure.
Here is what will qualify you for the role:
- 5+ years of experience in backend development in a cloud environment (Java/Spring preferred, AWS an asset).
- Strong understanding of building scalable and resilient distributed systems, with experience producing reusable code within complex infrastructures for large-scale applications.
- A problem-solving mindset, with the resourcefulness to analyze, optimize, and debug large-scale systems while continuously embracing a growth-oriented approach
Here is what would make you stand out:
- Familiarity with Terraform & Kubernetes for infrastructure automation and container orchestration.
- Experience with open-source ML serving frameworks.
Do you think you can bring this role to life? Send us your application, we want to get to know you!
Join the Coveolife!
We encourage all qualified candidates to apply regardless of, for example, age, gender, disability, gaps in CV, national or ethnic background. We know that applying for a new role is a lot of work and we really appreciate your time.
#li-hybrid
Top Skills
What We Do
Coveo powers the digital experiences of the world’s most innovative brands serving millions of people and billions of interactions across every digital experience. After a decade of enriching our market-leading platform with forward-thinking global enterprises, we know what it takes to gain a trusted AI-experience advantage.
We strongly believe that the future is business-to-person, that experience is today’s competitive front line, a make or break for every business.
For enterprises to achieve this AI-experience advantage at scale, it is imperative to have an Enterprise Spinal and composable ability to deliver AI semantic search and generative experiences at each customer and employee interaction.
_0.png)
