Site Reliability Engineer (SRE) - AI GPU Clusters

We are looking for a Senior Site Reliability Engineer to join our Site Reliability Engineering (SRE) team. In this role, you'll drive the reliability, scalability, and performance of our platform, ensuring our systems remain stable as we grow. We value innovation and are seeking someone eager to bring fresh ideas – especially around building automation that reduces manual effort and improving distributed systems resilience. This isn't a top-down organization; our engineers are the ones who flag technical challenges and design the solutions. You will collaborate closely with Platform Engineering, Security, AI Platform, and Product teams to design durable systems and make data-driven operational decisions. WHAT YOU'LL DO * Collaborate with Engineering, Platform, and Security teams to embed SRE best practices early in system design. * Lead advancements in observability, monitoring, alerting, and incident-response workflows. * Analyze platform performance to contribute to cost-optimization, performance tuning, and resilience planning. * Build infrastructure and automation tooling that improves platform reliability and enhances deployment safety. * Diagnose and resolve complex production issues across distributed systems, and drive open post-incident reviews so failures translate into durable improvements. * Strengthen system consistency and author clear, concise documentation for runbooks and operational processes. WHO YOU ARE * 4+ years of experience in SRE, DevOps, platform engineering, or similar production-facing roles. * Strong problem-solving and debugging skills in distributed systems to maintain higher platform stability. * Eager to share operational guidelines, champion SRE practices across teams, and openly discuss what we can learn from system failures. * Excellent communication skills (English is our default language) with a genuine, collaborative approach to working across diverse engineering teams. * Strong hands-on experience with cloud environments (AWS, GCP, or similar) and proficiency with infrastructure-as-code and CI/CD pipelines. * Familiarity with Kubernetes (or container orchestration), event-driven architectures, or supporting ML/AI workloads and GPU infrastructure. WHAT SUCCESS LOOKS LIKE: Within 3 Months: * Fully onboarded into the Rossum ecosystem, gaining a deep understanding of our infrastructure, observability stack, and SRE processes while building relationships across the team. * Gaining a deep understanding of our synergy with Coupa and our shared roadmap. * Initial Impact Goal: Improve a small reliability issue or add value to an existing automation or monitoring area. Within 6 Months: * Independently managing key responsibilities, owning recurring reliability tasks, and identifying areas for strategic improvement. * Actively participating in the alignment of processes within the new Coupa organizational structure. * Operational KPI: Implement measurable enhancements to alert quality, CI/CD reliability, or service health metrics. Within 12 Months: * Recognized as a subject matter expert within the team, navigating the global Coupa ecosystem. * Successfully contributing to Rossum's mission at a massive scale using new global resources. * Long-Term Strategic Goal: Lead a major reliability or infrastructure initiative, providing technical recommendations to guide our long-term reliability strategy. WHY JOIN US? At Rossum, we're on a mission to free the world from boring manual data entry. Our AI platform helps companies save millions of hours, allowing professionals to focus on creative, impactful work. In an exciting move for our future, we have joined forces with Coupa, the world's leading unified platform for Business Spend Management. By combining Rossum's cutting-edge document AI with Coupa's global ecosystem, we are uniquely positioned to redefine how businesses operate at a massive scale. You can read more about this exciting milestone and our shared vision in the official announcement here. What sets us apart? * Cutting-edge AI technology reshaping how businesses operate globally. * A collaborative, supportive environment where autonomy thrives. * Opportunities to grow in a fast-scaling company. * A culture that values diversity, empathy, and genuine connection. As part of the Coupa family, you'll enjoy the agility of a fast-moving, innovation-focused team with the stability and reach of a global market leader. For you, this means an even greater opportunity to make an impact, access new global markets, and grow your career within a collaborative culture that values autonomy, diversity, and genuine connection. Together, we're not just automating data—we're giving time back to the world's professionals. WHAT WE OFFER (BENEFITS) * Work-Life Harmony: 5 weeks of vacation, 5 sick/personal days, and a Birthday Day Off to celebrate you. For new parents, we offer an extra 18 weeks of fully paid Maternity leave and 8 weeks of fully paid Paternity leave. * Flexibility: Hybrid work model with flexible hours—find the balance that works best for you and work how you work best. * Tech & Setup: High-end laptop (MacBook) and tech setup. We also support you with personal development, including language lessons (English & Czech, on all levels). * Community & Well-being: Wellness Days (company-wide days to unplug, reset, and recharge), MultSport cards, regular team offsites, and meetups, in a friendly, ambitious team environment. Ready to make an impact in your next role? Apply now!

WHO WE ARE 🌍 Creating content that resonates is great — turning that attention into growth is even better. That's what Manychat does. Our AI-powered automations help creators and brands engage with audiences across Instagram, Messenger, WhatsApp, and TikTok — at the right moment, with the right message, minus the manual work. We're 400+ people across three continents behind the leading platform for conversational growth, with AI skills shaping how we build, how we work, and how we grow. WHO WE’RE LOOKING FOR 🌟 Want to shape an AI platform's architecture from day one, instead of just maintaining what someone else built? Manychat runs AI features for businesses worldwide, and we're hiring an SRE to own the reliability, performance, and cost of that AI infrastructure, and to raise the bar for how our whole engineering org builds on LLMs. This isn't a classical SRE role with a bit of AI sprinkled on top. We need someone AI-native: you already understand how modern LLM systems behave in production, things like token throughput, provider rate limits, degraded model quality, and inference latency tails, and you treat all of that as a first-class reliability concern, not an afterthought. Why this role is worth your time: * The AI Platform is still young, so you'll shape its architecture, standards, and roadmap from the ground up. * The stakes are real. AI features sit right in the critical path of customer-facing automation, so your work actually matters to the business, not just to a dashboard. * You'll partner directly with the Head of Infrastructure, with real autonomy and visibility into how your decisions play out. Sound like the kind of ownership you've been looking for? WHAT YOU'LL DO 🚀 * Own reliability and performance of our AI infrastructure: AI Gateway, inference services, and integrations with Amazon Bedrock, Azure OpenAI, and other LLM providers. * Design and evolve the AI Gateway: routing, failover between providers, rate limiting, caching, and guardrails. * Build observability for AI systems: latency/throughput/error SLOs per model and provider, token-level metrics, quality and drift signals. * Drive cost optimization and FinOps for AI workloads: per-feature cost visibility, model right-sizing, caching strategies, provider mix. * Run capacity planning and incident response for inference services; write and improve runbooks and postmortems. * Scale AI expertise across the org: set standards, review designs, and coach teams shipping LLM-backed features. TO SHINE IN THIS ROLE 💥 You’ll need: * 5+ years in SRE / platform / infrastructure engineering, including production ownership at significant scale. * Hands-on experience operating LLM-backed systems in production: provider APIs (Bedrock, OpenAI, Anthropic, or similar), inference pipelines, self-hosted or managed model serving. * Deep cloud-native background: AWS, Kubernetes, Terraform/IaC, CI/CD. * Strong observability practice (Prometheus/Grafana, OpenTelemetry, or equivalent) and experience defining SLOs for non-deterministic systems. * Proven cost-optimization work: you can show where you cut cloud or inference spend and how you made cost visible. * Staff-level influence: you've set technical direction beyond your own team and brought others along It would be great if you have: * Experience building or operating an LLM gateway/proxy (e.g., LiteLLM, Kong AI Gateway, custom). * Experience with GPU workload optimization, quantization, or serving frameworks (vLLM, TGI, Triton). * Experience with eval pipelines and quality monitoring for LLM outputs. WHY THIS ROLE * Green-field ownership: the AI Platform is young; you'll shape its architecture, standards, and roadmap. * Real scale and real stakes: AI features sit in the critical path of customer-facing automation. * Direct partnership with the Head of Infrastructure; high autonomy and visibility. WHAT WE OFFER 🤗  We care deeply about your growth, well-being, and comfort: * 🌍 Hybrid onboarding to start work remotely and relocation support for you and your family. * 💙 Comprehensive health insurance for both you and your family. * 📚 Professional development budget for conference tickets, online courses, and other relevant resources to help you grow. * 🫶 Flexible benefits package: no one-size-fits-all perks here. You get a budget and you decide where it goes, from health and wellbeing to family and setting up your home office. * 🪴 Hybrid work and generous, flexible time off — planned with your team, not rationed by a rigid quota. * 🍽️ In-office perks, including free meals and snacks. * 🤝 Company-funded sport activities, annual offsites and team-building events. * 🤖 AI isn't a perk here — it's how we work. Claude, OpenAI, and more are on by default from day one, and we back teams in adopting whatever makes them faster. Manychat is an Equal Opportunity Employer. We’re committed to building a diverse and inclusive team. We do not discriminate against qualified employees or applicants because of race, color, religion, gender identity, sex, sexual preference, sexual identity, pregnancy, national origin, ancestry, citizenship, age, marital status, physical disability, mental disability, medical condition, military status, or any other characteristic protected by local law or ordinance. This commitment is also reflected through our candidate experience. If you have individual needs that may require an accommodation during the interview process, please indicate this in your application. We will do our best to provide assistance throughout your interview process to ensure you’re set up for success.