About the role
About the role
We are looking for founding members to own the production infrastructure behind Inco's inference platform. You will take highly optimized inference engines and make them run reliably and efficiently on large GPU clusters serving customer traffic 24/7. The work spans Kubernetes, orchestration, traffic management, deployments, observability, and capacity, with the goal of infrastructure that ships continuously without interrupting customers and recovers from failures on its own.
You bring deep expertise in distributed production infrastructure, and you will work closely with the researchers and engineers who build our inference engines to learn what it takes to run them at scale. Exposure to LLMs is a plus. Our organization is flat, and you will carry ideas from inception through deployment.
About you
You have operated large-scale, always-on production infrastructure and understand what it takes to keep complex distributed systems reliable
You are exceptional at debugging complex failures across applications, infrastructure, networking, and distributed systems
You think about systems end-to-end: how traffic enters the system, gets routed and scheduled, reaches compute, and ultimately serves the customer
You automate recurring operational work rather than accepting it as permanent toil
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
Strong generalist engineering ability across Linux, networking, containers, Python, Bash, and distributed systems
Deep hands-on experience operating Kubernetes in production
Experience operating high-throughput, highly available production systems at significant scale
Strong understanding of cluster orchestration, scheduling, service discovery, load balancing, and traffic management
Experience building production observability using metrics, logs, dashboards, and actionable alerting
Strong understanding of networking fundamentals and how network behavior affects distributed applications
Experience designing safe deployment and rollout strategies for always-on production systems
Bonus
Experience operating large-scale AI systems, ML platforms, data platforms, or other compute-intensive distributed systems
Experience operating GPU clusters or AI/ML workloads
Familiarity with GPU environments including NVIDIA drivers, CUDA, NCCL, and InfiniBand/RDMA
Familiarity with LLM inference and serving stacks such as PyTorch, vLLM, SGLang, or TensorRT-LLM
Experience running bare-metal GPU fleets across multiple infrastructure providers
Experience with infrastructure-as-code tools such as Terraform
Compensation & Benefits
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.
About Inco
Inco AI (
inco.ai
) builds the agent-native inference platform for tomorrow’s token economics, making advanced AI fast enough for real workflows and affordable enough to use at scale. We’re the researchers and engineers behind AWQ, DFlash, and TensorRT-LLM, bringing frontier research into production.
Our platform ranked #1 in output speed on Artificial Analysis for every model we launched with, and our DFlash models have surpassed 10 million downloads on Hugging Face. Backed by B Capital, E14 Fund, and Tectonic Ventures, we serve customers across serverless, dedicated, and local AI deployments.