Responsibilities

Design internal APIs and abstractions that let engineers provision AI-ready environments through single-command automation.

Build type-safe internal tooling and AI agents in Go and Python for root-cause analysis, disaster recovery, and infrastructure optimization.

Architect asynchronous processing systems with Kafka and RabbitMQ for infrastructure scaling and high-volume data ingestion.

Maintain Docker and Kubernetes deployment standards across models, prompts, and application code.

Manage GPU workloads, Redis distributed caches, vector databases, and AI-specific observability metrics.

Monitor systems with Prometheus, Grafana, and ELK to support high throughput, resilience, and zero-downtime operations.

Requirements

- 8+ years of experience in platform infrastructure engineering supporting AI application development and platform self-service.
- High proficiency in Go.




- Hands-on experience with LLM APIs, prompt engineering, RAG pipelines, vector databases, and distributed caches.
- Deep experience with Kubernetes and asynchronous message streaming using Kafka or RabbitMQ.
- Strong background in monitoring with Prometheus, Grafana, and ELK and maintaining operational resilience.

Advantages

Primarily in-office work from the Bangalore office, except during PTO, work travel, or other approved leave.

Flexible time off, wellness resources, and company-sponsored team events.

Growth and development support, inclusive employee resource groups, and an inclusive workplace.

Workplace accommodations are available throughout the hiring process for candidates with disabilities.

📌 Technical Assistant - Flexible Working (Bengaluru)
🏢 Pure Storage
📍 Bengaluru