The future of AI is inference
With the rise of agentic workflows and reasoning models, enterprises now need 100x more compute and 10x more throughput to run state-of-the-art AI models. Building robust, scalable inference systems has become a top priority—but it's also a major bottleneck, requiring deep expertise in low-level systems, snapshotters, Kubernetes, and more.
Tensorfuse removes this complexity by helping teams run serverless GPUs in their own AWS account. Just bring:
We handle the rest—deploying, managing, and autoscaling your GPU containers on production-grade infrastructure. Teams use Tensorfuse for:
As a Founding Engineer focusing on Systems/Infrastructure, you will be at the forefront of building scalable infrastructure for AI inference. You'll be working on challenging technical problems in an emerging market, architecting and implementing backend services, optimizing container startup times, and ensuring high reliability and security of our infrastructure.
The role requires a strong background in Go and Kubernetes, with experience in cloud infrastructure and a methodical approach to debugging complex systems. You'll be joining an early-stage company where your work will have direct impact on shaping the future of AI infrastructure.
This is an in-person role at our Bangalore office, ideal for someone excited about working in a fast-paced startup environment and making significant contributions to the AI infrastructure landscape. The position offers competitive compensation (₹2.5M - ₹4M INR) and equity (0.50% - 0.80%), reflecting the founding nature of the role.