About The Position

Inco AI is seeking founding members to build systems that serve frontier models at scale, including kernels, runtimes, batching, KV cache, load balancing, and scheduling. The role focuses on improving inference latency, throughput, and cost per token across the serving stack, with deeper work in runtimes, kernels, quantization, or speculative decoding when that offers the highest leverage. As a founding engineer, you will own outcomes end to end and take work from first principles and prototype through production serving. The team is flat, and the role offers the opportunity to help establish the next standard in AI inference infrastructure. Inco AI builds an agent-native inference platform intended to make advanced AI fast enough for real workflows and affordable to use at scale. The company describes its team as researchers and engineers behind AWQ, DFlash, and TensorRT-LLM. Its platform ranked first in output speed on Artificial Analysis for every model it launched with, and its DFlash models have surpassed 10 million downloads on Hugging Face. The company serves customers across serverless, dedicated, and local AI deployments and is backed by B Capital, E14 Fund, and Tectonic Ventures.

Requirements

  • Experience optimizing latency- and throughput-critical inference across the full stack, from kernels and systems to the model layer.
  • Familiarity with modern GPU systems and deployment architectures, including HGX B300 and GB300 NVL72.
  • Familiarity with serving infrastructure, gateways, and inference stacks such as Kubernetes, NVIDIA Dynamo, Kong, SMG, PyTorch, vLLM, SGLang, and TensorRT-LLM.
  • Working knowledge of modern LLM and multimodal architectures, including quantization and speculative-decoding tradeoffs.
  • Production proficiency in Python and at least one systems language: Rust, C++, or Go.
  • Ability to work across the system, take end-to-end ownership of performance metrics, embrace ambiguity, and act decisively.
  • Fluency with coding agents and modern AI/ML workflows, and willingness to push the boundaries of what is possible with agents.
  • Interest in the risks and opportunities of an early-stage startup and a tech-lead mentality regardless of title or years of experience.

Nice To Haves

  • Hands-on experience authoring kernels with CUDA, Triton, or PTX.
  • Experience profiling, tracing, and debugging across model, runtime, kernel, and network layers using tools such as Nsight Systems (nsys).
  • Experience with batching, KV-cache management, and scheduling strategies.
  • Knowledge of quantization formats and algorithms, including NVFP4, FP8, PTQ, QAT, and QAD.
  • Familiarity with system-level inference optimization for NVL72-scale deployments, including wide expert parallelism, disaggregated prefill and decode, and related high-bandwidth interconnect techniques.
  • A track record of running inference workloads across 1,000+ GPUs.
  • A background in HPC or other high-performance systems.
  • Contributions to open-source ML or systems infrastructure.

Responsibilities

  • Build and optimize systems serving frontier models at scale, including kernels, runtimes, batching, KV cache, load balancing, and scheduling.
  • Improve inference latency, throughput, and cost per token across the serving stack.
  • Pursue performance improvements in runtimes, kernels, quantization, or speculative decoding where they offer the highest leverage.
  • Own performance outcomes end to end rather than limiting work to a single system layer.
  • Carry work from first principles and prototype through production serving.
  • Use coding agents and modern AI/ML workflows as part of the development and delivery process.

Benefits

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