Senior Customer AI Engineer - Token Factory

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Senior Customer AI Engineer – Token Factory based in Switzerland. Join an innovative AI infrastructure environment focused on helping businesses bring advanced AI applications from experimentation to reliable production at scale. In this role, you will bridge engineering, delivery, and customer success, ensuring AI workloads perform efficiently and reliably in real-world environments. You will guide customers through the transition from proof of concept to production while optimizing performance, scalability, cost, and system reliability. Working closely with customer engineering teams and internal product and infrastructure specialists, you will troubleshoot complex challenges and deliver practical technical solutions. You will also play a key role in managing production incidents and identifying opportunities for continuous improvement. This is an opportunity to combine deep technical expertise, customer collaboration, and end-to-end ownership while contributing to the evolution of modern AI infrastructure.

Lead the transition from proof of concept to production Own the customer journey from initial proof of concept (PoC) through production deployment and ongoing scaling. Ensure customer AI workloads are deployed successfully, remain stable, and scale to meet evolving business requirements. Accelerate time-to-production and time-to-value by identifying and addressing technical obstacles throughout implementation. Optimize AI workload performance and reliability Develop a thorough understanding of customer architectures, AI use cases, and infrastructure requirements. Monitor and improve inference performance, including latency, throughput, resource utilization, and cost efficiency. Identify performance bottlenecks, investigate root causes, and implement practical solutions to improve system reliability and scalability. Apply best practices for inference frameworks and AI infrastructure to support efficient production workloads. Serve as a trusted technical partner Work directly with customer engineering teams, machine learning specialists, and other technical stakeholders to ensure successful AI deployments. Provide guidance on implementation best practices, performance optimization, troubleshooting, and production readiness. Translate complex technical challenges into clear recommendations and actionable solutions. Collaborate with Solution Architects and internal engineering teams to align customer requirements with platform capabilities. Coordinate production incidents and technical risks Act as a primary technical point of contact for production-related issues and deployment challenges. Coordinate incident investigation and resolution with internal Product, Infrastructure, and Engineering teams. Communicate clearly with customers during high-pressure situations, providing timely updates and driving issues toward resolution. Identify potential risks proactively and implement measures to minimize disruption to customer workloads. Drive continuous improvement and customer outcomes Identify opportunities to optimize existing deployments, improve customer outcomes, and expand the effective use of AI infrastructure. Gather structured feedback from real-world customer deployments and communicate insights to Product and Infrastructure teams. Contribute to improvements in platform capabilities, deployment practices, and operational processes. Help develop scalable approaches that improve the overall customer experience and support long-term adoption. Requirements: Practical experience with AI inference frameworks such as vLLM, TensorRT, or similar technologies , with an understanding of their application in production environments. Strong understanding of cloud infrastructure, distributed systems, or high-load applications, including the technical challenges associated with scalable production deployments. Familiarity with AI and machine learning workloads, particularly large language models (LLMs), model inference, and the infrastructure required to serve them efficiently. Proven ability to troubleshoot complex technical issues, investigate system behavior, identify performance bottlenecks, and develop effective solutions. Experience working directly with technical customers, such as software engineers, machine learning teams, or infrastructure specialists. Excellent communication skills, with the ability to explain complex technical concepts clearly and adapt communication to different audiences. A strong sense of ownership and accountability, with a focus on delivering measurable outcomes rather than simply completing assigned tasks. Ability to manage multiple customer engagements, competing priorities, and technical challenges in a fast-moving environment. A structured, proactive, and solution-oriented mindset, with the confidence to investigate problems independently and coordinate the right resources when needed. Strong collaboration skills and the ability to work effectively with customer engineering teams, Solution Architects, Product teams, and Infrastructure specialists. The following experience is considered an advantage: Hands-on experience with GPU workloads, AI infrastructure, or large-scale model inference environments. Previous experience in solutions engineering, site reliability engineering (SRE), or technical support within business-to-business (B2B) technology environments. Experience helping customers deploy, optimize, and maintain complex cloud-based or AI-powered applications in production. Benefits: Competitive compensation: An attractive compensation package aligned with your expertise and experience. Career growth: Opportunities to develop your technical expertise and progress professionally in a rapidly evolving AI infrastructure environment. Continuous learning: Exposure to advanced AI technologies, inference frameworks, and real-world production challenges. Remote work flexibility: Work remotely from within Europe, with the opportunity to manage your work effectively and independently. Ownership and autonomy: Take responsibility for customer outcomes and influence technical decisions that directly affect production success. Collaborative culture: Work alongside talented engineers and specialists in an international, innovative, and fast-moving environment. Meaningful technical impact: Help businesses move AI applications into production and improve the performance, reliability, and cost efficiency of their workloads. Cross-functional collaboration: Partner with customer engineering teams and internal specialists across product development, infrastructure, and AI engineering. Opportunity to shape AI infrastructure: Contribute insights from real-world customer deployments to improve platform capabilities and support the future of AI.