A complete application in a minute
Tailored resume and cover letter, ready to send.
Inco AI is seeking a founding engineer to own kernel-level performance across our inference stack, identifying bottlenecks, fusing GPU kernels, and pushing improvements to production on traditional GPUs or custom accelerators.
This hands-on role has broad ownership with no middle layer; you set direction, work across hardware-software boundaries, and ship high-impact performance gains.
Strong preference for in-person work in Palo Alto or Brooklyn, with a highly competitive salary and equity.
We are looking for a founding engineer to own kernel-level performance across our inference stack. You will identify bottlenecks, write and fuse GPU kernels, use agents to automate kernel optimization, and carry improvements through to production.
This is a deeply hands-on role with wide ownership. You will define projects from first principles, work across the hardware–software boundary, and pursue the performance gains that matter most, whether on conventional GPUs or emerging custom accelerators. There is no management layer between you and the work: you will set the direction and ship it.
You work close to the metal and reason deeply about performance and system design
You work fluidly across the hardware-software boundary, and optimize as readily for traditional GPUs as for custom accelerators
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
Deep expertise in GPU and hardware performance optimization
Hands‑on experience with low‑level GPU kernel programming using CUDA, Triton, or PTX
Experience optimizing inference through kernel fusion, quantization, speculative decoding, or sparsity
Proficiency with profiling and tracing tools, including Nsight Systems and Nsight Compute (nsys, ncu)
Working knowledge of modern LLM and multimodal model architectures
Experience optimizing kernels and communication for LLMs on modern GPU systems like B300 and GB300 NVL72
Familiarity with custom accelerators and non-CUDA backends
Experience with GPU kernel libraries such as CUTLASS, cuBLAS, NCCL, CuTe DSL, and others
Familiarity with kernel-optimization agents and orchestration tools, such as KDA, AKO, Humanize, and agent frameworks for coordinating evaluation, iteration, and deployment
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.
Inco AI (inco.ai) builds the agent-native inference platform for tomorrow’s token economics. We build the inference layer that makes advanced AI fast enough for real workflows and affordable enough to use at scale. Agents are at the center of our work: when a single task chains dozens of model and tool calls, every gain in speed, cost, and reliability compounds.
We’re the researchers and engineers behind AWQ, DFlash, and TensorRT-LLM, with decades of combined leadership in AI efficiency and prior successful exits. Our team connects frontier research with the engineering needed to bring fast, reliable inference to production at scale.
We operate on five principles:
Operate at the frontier. The field moves every day, and so do we. We reinvent ourselves constantly and push the frontier forward with our research. We keep process light and decisions fast, so a good idea reaches production in days, not quarters. Legacy doesn’t slow us down.
Mission over individuals. We are obsessed with our customers and humble in pursuit of the goal. We share credit, name mistakes early, and change our minds when the evidence says so. The question is always what moves the mission forward, never who was right.
Amplify with agents. Code is free now; architecture and process aren’t. We hand agents everything they can own, from code to operations, and spend our own time on design, judgment, and the problems only people can solve.
Protect the maker’s time. Focus is our scarcest resource. We keep meetings few and protect long, uninterrupted stretches of work. We automate overhead, cover meals, and handle logistics, so our hours go to research and product.
Be a team player. We win as one team. We share context generously, step in wherever we’re needed, and hold each other to a high bar, because exceptional work comes from exceptional peers.