Builds and maintains infrastructure components for ML inference platform using Python and Go. Implements Kubernetes deployments, monitoring systems, and resource management for efficient model serving, requiring Kubernetes knowledge and ML basics.
165k – 330k/yr
HybridDevOps / SRE
About the role
Responsibilities
Develop infrastructure components for our ML inference platform using Python and Go
Implement and maintain Kubernetes deployments for model serving
Contribute to our inference orchestration layer for model deployments
Build and enhance monitoring systems for model performance metrics
Implement efficient resource management solutions for ML workloads
Support infrastructure automation to improve ML deployment workflows
Work closely with team members to implement technical solutions
Help balance performance optimization with system reliability
Participate in technical discussions around infrastructure improvements
Learn and apply infrastructure best practices
Requirements
Bachelor's degree or higher in Computer Science or related field
Proficient coding abilities in one or more popular programming or scripting languages; Go proficiency is a plus
Working knowledge of Kubernetes and containerization
Basic understanding of machine learning concepts and model serving
Familiarity with distributed systems concepts
Experience with basic monitoring and logging tools
Interest in ML/AI infrastructure and willingness to learn
Infrastructure Engineer responsible for securing, scaling, and maintaining cloud architecture, Kubernetes clusters, ML pipelines, and CI/CD systems at a computer vision AI startup. Must have production Kubernetes, IaC, and AWS/GCP experience.
165k – 200k/yr
HybridDevOps / SRE
DevOps Engineer
OctusNew York, NY
Design, implement, and maintain cloud infrastructure and CI/CD pipelines. Collaborate with developers, SRE, and Security to ensure system reliability, scalability, and security.
165k – 190k/yr
On-site5+ YOEDevOps / SRE
OS / K8s Systems Engineer
BasetenSan Francisco, CA +1
Build automation and systems to provision and orchestrate GPU hardware into scalable Kubernetes clusters. Requires deep Linux expertise, provisioning experience, and strong programming in Python/Go.
165k – 330k/yr
HybridDevOps / SRE
Site Reliability Engineer (SRE)
BasetenSan Francisco, CA +1
Site Reliability Engineer builds and maintains scalable infrastructure for ML model deployment, automates CI/CD pipelines, and ensures reliability using tools like Kubernetes and Terraform. Collaborates cross-functionally, owns projects end-to-end, and mentors juniors; bachelor's in CS or related field required.
165k – 330k/yr
HybridDevOps / SRE
Software Engineer - Internal Platform
BasetenSan Francisco, CA +1
Builds internal tooling, monorepos, CI/CD pipelines, and shared libraries to boost engineering productivity. Requires strong proficiency in Go/Python, Kubernetes/Docker experience, and monorepo management.