About The Position

Inco AI is seeking a founding engineer to own kernel-level performance across its inference stack. The role involves identifying bottlenecks, writing and fusing GPU kernels, using agents to automate kernel optimization, and taking improvements through to production. It is a deeply hands-on position with broad ownership: the engineer will define projects from first principles, work across the hardware–software boundary, and pursue meaningful performance gains on conventional GPUs and emerging custom accelerators. There is no management layer between the engineer and the work; the engineer will set direction and ship improvements. Inco AI builds an agent-native inference platform focused on making advanced AI fast enough for real workflows and affordable at scale. The company says its team has worked on AWQ, DFlash, and TensorRT-LLM, and that its platform ranked first in output speed on Artificial Analysis for every model it launched with. Its DFlash models have surpassed 10 million downloads on Hugging Face. Inco AI is backed by B Capital, E14 Fund, and Tectonic Ventures, and serves customers across serverless, dedicated, and local AI deployments.

Requirements

  • 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 such as B300 and GB300 NVL72.

Nice To Haves

  • Familiarity with custom accelerators and non-CUDA backends.
  • Experience with GPU kernel libraries such as CUTLASS, cuBLAS, NCCL, and CuTe DSL.
  • Familiarity with kernel-optimization agents and orchestration tools such as KDA, AKO, Humanize, and agent frameworks for coordinating evaluation, iteration, and deployment.

Responsibilities

  • Own kernel-level performance across the inference stack.
  • Identify performance bottlenecks and write and fuse GPU kernels.
  • Use agents to automate kernel optimization.
  • Carry performance improvements through to production.
  • Define projects from first principles and work across the hardware–software boundary.
  • Set technical direction and ship performance improvements.

Benefits

  • Highly competitive salary and equity.
  • Comprehensive health coverage for the employee and dependents.
  • Strong 401(k) match.
  • Meals and snacks provided.
  • Discretionary productivity budget.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service