Deci.AI is on a mission to empower AI developers by providing them with robust tools to create innovative AI-based solutions. Our goal is to guarantee that these models not only excel in production but also unlock their full potential.

Join us in shaping the future of AI, where innovation meets empowerment at every level.

We’re looking for a full-stack engineer who can solve complex system architecture challenges in the cloud, write production-grade code, and be familiar with the most advanced design methodologies.

The ideal candidate should be familiar with building solutions that use container orchestration tools (e.g., Docker, Kubernetes).

Deci’s full-stack engineers work closely with deep learning engineers and scientists and become experts in the machine and deep learning production pipelines.

Requirements

• B.Sc. degree in computer science, a related field, or equivalent practical experience
• 5+ years experience as a backend engineer in an industrial cloud environment
• Experience in Linux/Unix systems
• Previous experience with Docker, Kubernetes, and container-based solutions
• Previous experience building cloud-native applications
• Proficient in Python programming and extensive knowledge of OOP, design patterns, and SOLID principles
• Experience with frontend development with React, Typescript, and Javascript
• Prior experience with unit, integration, and functional testing
• Excellent team player with strong communication skills in verbal and written English
• Familiarity with DevOps practices and tools

Preferred Qualification

• Experience in deploying machine learning or deep learning
• 6+ years of experience as a backend engineer in an industrial cloud environment
• Prior experience building CI/CD pipelines with Jenkins/CircleCi
• Experience working with microservices
• Experience working with serverless frameworks
• Experience building a core middleware architecture for on-premise integration

Responsibilities

• Design, deploy, and maintain cloud-agnostic managed services that orchestrate various LLMs at large scale and truly performant-oriented environments
• Integrate the latest state-of-the-art abilities into generative AI K8s clusters—own large features end-to-end, from product refinement to design reviews and through to deployment
• Lead and guide front and backend web development using agile methodologies. Deliver efficient and high-quality B2B solutions and see their deployment through
• Profile and debug cloud performance and scaling bottleneck, meeting and improving Deci’s latency and throughput SLAs