About the role
About the role
This is our open application for founding members who want to work on the hardest problems in AI inference. Apply here if you aren't sure which of our roles fits you, if the role you'd want doesn't exist yet, or if your work spans several disciplines.
You'll work closely with our researchers and engineers to identify where you can make the biggest contribution, whether that's developing new research ideas, building core systems, or bringing advances in inference into production.
About you
You have a track record of taking ambiguous technical problems from zero to shipped results, in research, systems, or production
You go where the leverage is, moving between models, systems, kernels, and infrastructure rather than staying in one layer
You would rather own an outcome end to end than a single component, and you pick up new domains quickly
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
Exceptional depth in at least one area of AI inference: model research and post-training, quantization or speculative decoding, GPU kernels, serving systems and runtimes, or large-scale distributed infrastructure
Working knowledge of modern LLM and multimodal architectures and the performance tradeoffs behind them
A track record of shipping technical work others depend on, through publications in relevant venues (NeurIPS, ICLR, ICML, MLSys, ...), open-source contributions, or production systems
Production proficiency in Python and at least one systems language: Rust, C++, or Go
Bonus
Hands-on experience with open-source inference and serving stacks such as PyTorch, vLLM, SGLang, Dynamo, SMG, and TensorRT-LLM
Hands-on experience authoring GPU kernels with CUDA, Triton, or PTX
Experience with quantization (NVFP4, FP8, PTQ, QAT, QAD) or speculative decoding (DFlash, EAGLE-3)
Familiarity with system-wide profiling, tracing, and debugging using tools such as Nsight Systems (nsys)
Experience with on-device inference or accelerators beyond NVIDIA and AMD
A track record of operating inference workloads across 1,000+ GPUs
Contributions to open-source ML or systems infrastructure
Compensation & Benefits
Highly competitive salary 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.