Title: Senior AI Platform & Infrastructure Engineer
Location: Bangalore
Experience: 8+ Years
Work Mode: Hybrid
Job Description:
Were looking for an experienced Infrastructure Engineer with a strong background in Kubernetes (K8s), GPU-based workloads, and scaling large distributed systems. We need builders, not just maintainers. Ideal candidates will have hands-on experience developing and stress-testing infrastructure at scale, not just reporting bottlenecks, but solving them.
What Youll Do
- Design, build, and optimize infrastructure and develop backend to support large-scale, GPU-accelerated workloads.
- Work with frameworks like LangChain, LlamaIndex, LangGraph and other custom agentic systems.
- Develop and run performance/stress tests to identify and resolve scaling issues.
- Own the infrastructure layer: from container orchestration to system-level performance tuning.
- Collaborate with engineering teams to ensure infra scales with product needs.
- Architect scalable cloud infrastructure (AWS/GCP/Azure).
What Were Looking For
- Strong experience with Python or Node.js for backend systems (Python preferred for AI work).
- Deep hands-on experience with Kubernetes, Terraform, Docker and GPU-based workloads.
- Proven ability to design, test, and scale large systems (not just monitor them).
- Experience with async frameworks (FastAPI, NodeJS Async).
- Track record of solving infra scaling problems, not just escalating them.
- Strong understanding of distributed systems performance, observability, and tuning.
Interested candidates can share their updated CV on Sanaa@norwintechnologies.com
Sana Azmi
Talent Acquisition Specialist