Lead the effort to make Runpod the fastest and most cost-efficient place for LLM inference, owning performance end to end.
Profile and diagnose performance bottlenecks across the serving stack, from scheduling to kernels, and implement fixes.
Work closely with product and infrastructure teams to shape how inference is offered, turning improvements into production-ready defaults.
Runpod is the AI Developer Cloud, providing a platform for over one million developers to experiment, train, fine-tune, deploy, and scale AI. We're a small, remote-first team that takes ownership seriously, moves fast, and has processed more than 20 billion inference requests.
Lead end-to-end technical deployments for GPU neocloud and AI Factory customers.
Configure and troubleshoot bare metal GPU infrastructure including CNI, GPU Operator, and storage.
Build playbooks and transfer knowledge to customer teams for self-sufficiency.
vCluster Labs provides a platform for AI infrastructure, helping GPU cloud providers and enterprises build Kubernetes-based clusters. They are a venture-backed startup with 40+ engineers and a remote-first culture, powering over 100,000 GPUs.
Operate and expand Telnyx's own B300 GPU fleet to maximize inference throughput per GPU-dollar.
Design and implement serverless inference for open-weight models and dedicated enterprise deployments.
Work upstream in open-source technologies like vLLM, SGLang, and Kubernetes.
Telnyx is an industry leader building the future of global connectivity through a private, multi-cloud IP network and edge APIs. The company is financially stable and profitable, with a global team and a focus on innovation and continuous learning.
Own end-to-end ML systems from data and training to evaluation, inference, and deployment.
Build and evolve training, fine-tuning, and inference infrastructure for large models.
Partner with research and application engineering to turn model capabilities into product improvements.
Next Step Systems is an IT recruiting and staffing agency that connects companies with machine learning and technology talent. They specialize in placing candidates in remote and on-site roles across the United States and emphasize a fast-paced, results-oriented culture.
Lead the architecture and delivery of a large-scale GPU infrastructure platform, evolving from managed Kubernetes to bare-metal with Slurm and inference support.
Manage a distributed engineering team across backend, frontend, DevOps, QA, and documentation, setting technical standards and overseeing implementation.
Own GPU infrastructure operations, including Slurm, Kubernetes, NVIDIA hardware, observability, and incident response, while acting as the primary technical interface with partners.
Jobgether is an AI-powered job matching platform that connects candidates with relevant roles, ensuring a fair and objective review process. It operates with a distributed team and partners with companies globally, focusing on efficient and transparent recruitment.
Execute GPU node and cluster bring-up, validation, and automated testing across new hardware platforms.
Troubleshoot GPU and OS hardware/software issues, maintaining drivers, firmware, and system software.
Automate infrastructure with Python, Bash, and Ansible while monitoring cluster health and documenting processes.
Vultr provides high-performance cloud compute, GPU, bare metal, and storage solutions across 33 global data centers. It is a privately-held, employee-focused cloud infrastructure company valued at $3.5 billion with hundreds of thousands of customers.
Owns the architectural direction for Code Metal's AI platform and the team building it.
Builds production-grade inference serving, model gateways, agent harnesses, and context-engineering services.
Instruments the stack end to end and drives experimentation and observability for reliable AI systems.
Code Metal provides automated software engineering using AI and formal verification to produce provably correct code. Founded in 2023 and backed by Accel, Salesforce Ventures, and others, it serves defense and enterprise customers from offices in Boston and San Francisco.
Lead the end-to-end machine learning lifecycle, from data preparation and model training to evaluation, inference, and deployment.
Build and optimize scalable training, fine-tuning, and inference pipelines for large-scale models on GPU infrastructure.
Establish production best practices for model quality, reliability, safety, and measurable performance improvements.
This company builds production-grade machine learning systems and large-scale GPU-powered inference pipelines. It is a fully remote team that values technical rigor, collaboration, and hands-on engineering.
Architect GPU cluster topologies spanning compute, networking, storage, and control planes.
Model AI workloads like LLM training and inference to guide performance tradeoffs.
Collaborate with cross-functional teams to deploy and scale reliable AI infrastructure.
This role is with a partner company focused on designing next-generation AI infrastructure at massive scale. The company fosters a fast-moving, engineering-led culture with a collaborative, international team.