Vetted technical experts, precisely matched: the engineers, researchers and maintainers behind the technology your client is asking about, with their work as proof.
Experts on LLM inference serving
CUDA engineer shipping kernels for graph ML and LLM serving
Works on GPU kernels and graph deep learning infrastructure. Commits to dmlc/dgl, a package for deep learning on graphs, and contributes to flashinfer-ai/flashinfer, a kernel library for serving large language models.
CRACKED
Active 2 days ago
Works on GPU kernels and graph deep learning infrastructure. Commits to dmlc/dgl, a package for deep learning on graphs, and contributes to flashinfer-ai/flashinfer, a kernel library for serving large language models.
3,891 contributions this year
ML systems engineer on Perplexity's LLM serving stack
Delivers distributed ML systems infrastructure at Perplexity. Lands changes in flashinfer-ai/flashinfer, a kernel library for serving large language models, and pushes to punica-ai/punica, a server for multiple LoRA finetuned language models.
CRACKED
Active 2 days ago
Seattle, United States
Delivers distributed ML systems infrastructure at Perplexity. Lands changes in flashinfer-ai/flashinfer, a kernel library for serving large language models, and pushes to punica-ai/punica, a server for multiple LoRA finetuned language models.
3,960 contributions this year
Sr. Director building LLM serving systems at Together AI
Drives LLM serving infrastructure at Together AI. Pushes to sgl-project/sglang, a serving framework for large language models, and works on kvcache-ai/Mooncake, a serving platform for large language models.
CRACKED
Active 12 days ago
San Francisco, United States
Drives LLM serving infrastructure at Together AI. Pushes to sgl-project/sglang, a serving framework for large language models, and works on kvcache-ai/Mooncake, a serving platform for large language models.
1,634 contributions this year
For research, recruiting and expert sourcing teams.
Step 1
Describe who you want in Claude, or send it to the API: a place, a company, a repo or the kind of work.
Step 2
Each person comes back with the repos they own and contribute to, their contribution garden, a cracked score and a one-line why.
Step 3
Keep a shortlist, write the fields to your CRM, or build them into your product over the API.
Run it in Claude, or build on the API. See how Vamo compares with Exa.
© 2026 Vamo Holdings, Inc.
