About the role
About the role
We are looking for founding members to lead frontier AI research projects and translate findings into production inference. The scope is deliberately broad: inference spans everything between a trained model and a served token.
The work can include post-training and fine-tuning, quantization, speculative decoding, and optimization across kernels, serving systems, and models. We’re looking for people who are not only comfortable moving between these layers, but prefer the flexibility to work wherever the highest-impact opportunity is.
We are the team behind industry-leading techniques like AWQ and DFlash, and this role will continue pushing that work forward. Our organization is flat, and every member contributes end to end, from research and inception through production serving.
About you
You have a track record of leading rigorous technical projects from zero, and are motivated to advance frontier research yourself.
You are comfortable working across the full inference stack and move fluidly between model, systems, and kernel layers
You are drawn to the risk and upside of an early-stage startup
You embrace ambiguity and have a strong bias for action
You operate with a tech-lead mentality regardless of title or years of experience
You treat AI as a force multiplier: fluent with coding agents and modern AI/ML workflows, you fold them into how you ship, and you are willing to push the boundary of what’s possible with agents
Requirements
Fluency in modern LLM and multimodal architectures, including training, fine-tuning, quantization, speculative decoding, and their tradeoffs
Depth in quantization formats and algorithms such as NVFP4, FP8, PTQ, QAT, and QAD
Familiarity with speculative-decoding methods including DFlash, EAGLE-3, and comparable approaches
Demonstrable research track record, either publications in relevant venues (NeurIPS, ICLR, ICML, MLSys, ...) or open-source contributions or similar
A record of taking model-level research from prototype to production inference
Hands-on experience with open-source inference and serving stacks such as PyTorch, vLLM, SGLang, Dynamo, SMG, and TensorRT-LLM
Bonus
Production proficiency in Python and at least one systems language: Rust, C++, or Go
Hands-on experience authoring GPU kernels with CUDA, Triton, or PTX
Familiarity with system-wide profiling, tracing, and debugging using tools such as Nsight Systems (nsys)
A track record of operating inference workloads across 1,000+ GPUs
Contributions to open-source ML or systems infrastructure
Compensation & Benefits
Highly competitive salary ($200,000–$350,000+) and equity
Comprehensive health coverage for you and your dependents
Strong 401(k) match
Meals and snacks on us + discretionary productivity budget
Strong preference for in-person in Palo Alto or Brooklyn.
About Inco
Inco AI (
inco.ai
) builds the agent-native inference platform for tomorrow’s token economics, making advanced AI fast enough for real workflows and affordable enough to use at scale. We’re the researchers and engineers behind AWQ, DFlash, and TensorRT-LLM, bringing frontier research into production.
Our platform ranked #1 in output speed on Artificial Analysis for every model we launched with, and our DFlash models have surpassed 10 million downloads on Hugging Face. Backed by B Capital, E14 Fund, and Tectonic Ventures, we serve customers across serverless, dedicated, and local AI deployments.