Member of Technical Staff, Inference Research

We are looking for founding members to lead frontier AI research projects and translate findings into production inference. The scope is deliberately broad: inference spans everything between a trained model and a served token.

The work can include post-training and fine-tuning, quantization, speculative decoding, and optimization across kernels, serving systems, and models. We’re looking for people who are not only comfortable moving between these layers, but prefer the flexibility to work wherever the highest-impact opportunity is.

We are the team behind industry-leading techniques like AWQ and DFlash, and this role will continue pushing that work forward. Our organization is flat, and every member contributes end to end, from research and inception through production serving.

About you

• You have a track record of leading rigorous technical projects from zero, and are motivated to advance frontier research yourself.
• You are comfortable working across the full inference stack and move fluidly between model, systems, and kernel layers
• 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

• Fluency in 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
• Demonstrable research track record, either publications in relevant venues (NeurIPS, ICLR, ICML, MLSys, ...) or open-source contributions or similar
• 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

• 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+ GPUs
• Contributions to open-source ML or systems infrastructure

• 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.

• Highly competitive salary ($200,000–$350,000+) 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 http://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.