About The Position

Inco AI is seeking founding team members to lead frontier AI research projects and translate findings into production inference. The role covers the full inference stack, from trained models to served tokens, and may involve post-training and fine-tuning, quantization, speculative decoding, and optimization across kernels, serving systems, and models. Team members are expected to work across these layers and focus wherever they can have the highest impact. The organization is flat, and each member contributes end to end, from research and project inception through production serving. The role continues Inco AI’s work on techniques such as AWQ and DFlash. The company strongly prefers in-person work in Palo Alto or Brooklyn. Inco AI builds an agent-native inference platform focused on making advanced AI fast and affordable for real-world workflows. The company says its platform ranked first in output speed on Artificial Analysis for every model it launched with, and its DFlash models have received more than 10 million downloads on Hugging Face. Inco AI is backed by B Capital, E14 Fund, and Tectonic Ventures, and serves customers through serverless, dedicated, and local AI deployments.

Requirements

  • A track record of leading rigorous technical projects from zero and motivation to advance frontier research.
  • Comfort working across the full inference stack, moving between model, systems, and kernel layers.
  • Fluency with 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.
  • A demonstrable research track record, such as publications at relevant venues, open-source contributions, or similar work.
  • 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.
  • Comfort with the risk and upside of an early-stage startup, ambiguity, and a strong bias for action.
  • A tech-lead mentality regardless of title or years of experience.
  • Fluency with coding agents and modern AI/ML workflows, and willingness to incorporate them into work and push the boundaries of what agents can do.

Nice To Haves

  • 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 or more GPUs.
  • Contributions to open-source ML or systems infrastructure.

Responsibilities

  • Lead frontier AI research projects from inception.
  • Translate research findings into production inference.
  • Work across the inference stack, including post-training and fine-tuning, quantization, speculative decoding, kernels, serving systems, and models.
  • Contribute end to end from research through production serving.

Benefits

  • 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