CORE WORK WILL INCLUDE:
- Building scalable infra for AI inference.
- Architecting and implementing backend services in Go and Python
- Extending our Kubernetes operators to optimise them for AI workloads
- Optimizing container startup times with custom snapshotters written in Go
- Ensuring high reliability of our infrastructure on AWS
- Ensuring infrastructure level security of AI workloads.
- Designing custom load balancing algorithms for LLMs, video and bio models in production.
YOU WOULD BE IDEAL FIT IF:
- 2-3 years of professional experience with Go and / or Kubernetes
- Familiarity with IaC tools like Cloudformation
- You are methodical in debugging complex systems by diving deeper into code.
- Philosophy: You will be working on a hard technical problem in an emerging market which requires committing at least two years to the problem. You will be an ideal fit if you are willing to take that risk.
BONUS:
- Experience with GPU workloads and ML inference (vLLM, SGLang etc) is a plus.
- Experience with working at a startup (between Seed to Series C stage).
This is an in person role at our office in Bangalore. We’re an early stage company which means that the role requires working hard and moving quickly. Please only apply if that excites you.