2 days ago
Responsibilities
- Design, build, and maintain scalable backend services and APIs using Go.
- Deploy, manage, and monitor LLM and ML model workloads in production environments.
- Develop and operate Kubernetes-based infrastructure, including controllers, operators, and Helm charts.
- Collaborate with product and platform teams to define API contracts and integration patterns.
- Lead technical discussions, conduct code reviews, and mentor junior engineers.
- Identify and resolve performance bottlenecks across service and infrastructure layers.
Requirements
- At least 5 years of professional software engineering experience in backend or infrastructure roles.
- Strong proficiency in Go, including idiomatic code, concurrency patterns, error handling, and testing.
- Solid understanding of Kubernetes workloads, scheduling, networking, and cluster operations.
- Hands-on experience deploying and serving LLM or ML models, such as with vLLM, TorchServe, Triton, or similar tools.
- Experience designing and implementing RESTful APIs, including versioning, error contracts, and authentication.
- Comfort working with cloud-native services and distributed systems.
- Experience with Temporal or Argo Workflows is preferred.
- Familiarity with GPU infrastructure, the NVIDIA operator, or ML acceleration technologies is preferred.
- Exposure to GitOps tools such as ArgoCD or Flux is preferred.
- Contributions to cloud-native or ML open-source projects are preferred.
Benefits
- Competitive base salary and equity options for India-based candidates.
- The company emphasizes ownership, autonomy, collaboration, and opportunities to contribute to a growing edge AI infrastructure company.
Tech Stack
Categories
About Armada
Welcome to the new edge. Armada is the world’s first full-stack edge computing platform, revolutionizing connectivity, compute, and AI solutions where they’re needed most - anywhere on Earth.