remote
Senior Software Engineer, Cloud Platform - zilliz
Software Engineer
Lead the design and scaling of a cloud‑native vector database platform, driving performance, reliability, and cost efficiency for enterprise AI workloads using Python, Go, Kubernetes, and AWS.
About the role
Key Responsibilities
- Architect and implement high‑throughput, low‑latency services in Python and Go for vector search and storage.
- Design and maintain Kubernetes‑based deployment pipelines, ensuring zero‑downtime releases and autoscaling.
- Collaborate with data‑engineering and ML teams to optimize query execution and indexing strategies.
- Implement observability, monitoring, and alerting across distributed services using Prometheus, Grafana, and OpenTelemetry.
- Drive performance tuning, cost‑efficiency improvements, and reliability hardening for production workloads.
Requirements
- 5+ years of production software engineering experience, preferably in cloud‑native environments.
- Strong proficiency in Python, Go, and C++ with a track record of building scalable distributed systems.
- Hands‑on experience with Kubernetes, Docker, and AWS services (EKS, S3, RDS).
- Deep understanding of gRPC, REST, and message‑queue patterns for inter‑service communication.
- Excellent problem‑solving skills, ability to work in a fast‑moving startup culture, and a passion for AI infrastructure.
Skills
pythoncgokubernetesawsdockergrpc