About Us
We are an early-stage deep tech startup building infrastructure software at the intersection of cloud computing and AI performance optimization. Our founding team comes from industry-leading organizations including Meta and Nvidia-acquired Grok. We are backed by experienced founders and working on a technically hard problem in AI inference and GPU workload optimization.
We do not share full product details publicly at this stage, but candidates who reach the interview will get the complete picture.
The Role
We are looking for a PhD candidate or doctoral researcher with strong hands-on experience in LLM deployment, GPU computing, and inference optimization. This is not a research-only role, we want someone who can move between theory and implementation, owns their work end to end, and is comfortable operating without established playbooks.
You will work directly with senior engineers and founders on real infrastructure problems.
What You Will Do
- Deploy and benchmark LLM inference workloads across GPU-accelerated cloud environments
- Work with frameworks including vLLM, LangChain, and LangGraph to build and evaluate AI pipelines
- Contribute to telemetry instrumentation and observability tooling for production AI systems
- Optimize inference performance, latency, throughput, GPU utilization, and surface actionable insights
- Assist with cloud deployment automation across AWS, GCP, or Azure
- Engage with cutting-edge research and apply findings directly to our platform
What We Are Looking For
- Currently enrolled in or recently completed a PhD program in Computer Science, Computer Engineering, Electrical Engineering, or a related field
- Deep understanding of LLM inference, GPU computing, and CUDA programming
- Hands-on experience with vLLM, CUDA, or similar GPU inference frameworks
- Strong familiarity with cloud infrastructure, AWS, GCP, or Azure
- Experience deploying and benchmarking models in production or research environments
- Comfort working independently in fast-moving, early-stage environments
- MCP (Model Context Protocol) experience is a plus
- Publications or research experience in ML systems, distributed computing, or AI infrastructure is a plus
Why This Role
- Work directly with founders who have built and scaled AI infrastructure at the highest level in the industry
- Real problems, your work ships and has impact
- Flexible hours and fully remote
- Path to full-time for the right candidate
- Opportunity to be part of something being built from the ground up at an inflection point in AI infrastructure