We are looking for an experienced Ray / Distributed AI Scheduling Engineer
This role owns the distributed AI scheduling layer.
What This Person Will Build
- Ray-based distributed task graphs for inference, training, RAG, vector search, document retrieval, video, and compound workloads.
- Ray head and worker deployment patterns on Kubernetes.
- Per-hardware workload drivers for GPU inference, vector search, storage retrieval, video acceleration, and edge inference.
- Model-locality and cache-awareness logic so workloads run near the right model or data.
- Integration between scheduling decisions, capacity state, SLA rules, billing events, and observability traces.
- End-to-end workload tests for compound RAG and multi-plane AI jobs.
Must-Have Background
- Strong Python distributed-systems experience.
- Real Ray experience, preferably production Ray, KubeRay, or distributed AI workload orchestration.
- Understanding of AI inference, training, RAG pipelines, model serving, model locality, and accelerator-aware scheduling.
- Kubernetes experience for deploying distributed compute systems.
- Debugging ability across Python, Kubernetes, GPUs, network movement, and application latency.
Nice to Have
- vLLM, TensorRT-LLM, KubeRay, vector search, RDMA storage, GPU scheduling, video pipelines, edge inference, or large-scale model-serving platforms.
Send your Resume / CV to apply online
Founded in California in 2004, Codeminders specializes in developing cutting-edge software solutions for high-tech companies in the Silicon Valley of California. Our expertise spans a wide range of industries, with a primary focus on modern technologies such as AI, mobile applications, video conferencing, and cloud computing.
As a member of the Codeminders team, you’ll have the unique opportunity to work on innovative projects. Whether it’s collaborating with dynamic startups or established companies serving millions of users, every project is a chance to shape the future of technology.
Why Codeminders?We believe in empowering our team members with the tools, opportunities, and culture to thrive. Here's what you can expect when you join us:
- Innovation at Its Core: Work on transformative projects that utilize the latest technologies, tools, and methodologies.
- Global Collaboration: Partner with world-class engineers from both the US and Ukraine, fostering diverse perspectives and international exposure.
- Strong Ethical Foundation: We stand firm in our values by maintaining zero business ties with Russia, Belarus, and temporarily occupied Ukrainian territories (Crimea, Donbas, etc.).
We offer a robust package designed to support your professional and personal growth:
- Competitive Compensation: Your salary is based on your qualifications, experience, and performance.
- Exceptional Stability: Enjoy job security and ample opportunities for career progression.
- Professional Development: Access educational programs and certifications to expand your expertise.
- Health & Wellness: Comprehensive support for fitness.
- Flexible Working Environment: Benefit from a fully remote work setup, flexible schedules, and relocation assistance if needed.
- Performance Recognition: Regular bonuses, annual salary reviews, and recognition for your achievements.
- Advanced Equipment Options: Choose the workstation setup that fits your needs, whether a desktop or laptop.
- Team Building & Community: Participate in regular events that foster collaboration, camaraderie, and innovation.
Skills Required
- Strong Python distributed-systems experience
- Experience with Ray in production environments
- Kubernetes experience for deploying distributed compute systems
- Understanding of AI inference and training processes
- Debugging ability across multiple technologies
What We Do
Ideas are born everyday, and they die just as quickly. That’s because the single hardest part of any new idea is actually going out and doing it. But today, startups and enterprises are running leaner than ever. Talent, quality talent, is in short supply, and development teams have less and less experience working with each other. Weak talent produces weak products, and rookie teams, make rookie mistakes. That’s why we built Codeminders, to provide startups and enterprises with access to our veteran team of experts who working together to turn big ideas into reality. Since 2004, we’ve been partnering with entrepreneurs, startups, and enterprises across the US and EU, from two man teams up to global Fortune 10 companies, collaborating to ship amazing products into the world. Established in Silicon Valley, Codeminders is a passionate, energetic team, split between the US and Eastern Europe. We focus on Big Data, Mobile & Internet of Things, and Web Development. With many complex projects under our belts, we’re a highly specialized, development powerhouse for entrepreneurs, startups, and enterprises. We have purposely designed a company based around our views on partnership, people, and process, and we bring these unique views to every project we take on. If you’re considering a development project, talk to our team. We’ll walk you through a brainstorming session where we can scope your project and explain how Codeminders works. It’s during this meeting that you’ll get a feel for our process and transparency and understand how we can build within your budget.
