Senior Sales Engineer - Token Factory

Accountabilities

• Lead in-depth technical discovery with engineering teams, technical founders, and other customer stakeholders to understand models, traffic expectations, latency requirements, GPU economics, and system dependencies.


• Translate customer objectives into production-ready architectures while identifying technical risks, scalability constraints, and hidden dependencies early.


• Partner closely with Sales on strategic opportunities, using architectural clarity to influence deal strategy and prevent technically misaligned commitments.


• Define measurable PoC success criteria covering latency, time to first token (TTFT), throughput, cost, and other relevant performance indicators.


• Assess workload complexity and determine the appropriate level of optimization, technical support, engineering involvement, and GPU capacity required.


• Drive structured Go/No-Go decisions and help ensure PoCs remain appropriately scoped, economically justified, and free from uncontrolled customization or hidden R&D requirements.


• Identify recurring customer configuration and workload patterns, quantify demand for advanced inference optimizations, and communicate structured insights to Product and Engineering.


• Contribute to the evolution of platform capabilities by turning real-world workload data and customer requirements into actionable product opportunities.


• Help ensure strategic deals are technically sound before engineering engagement, engineering resources are allocated predictably, and customers receive scalable solutions.

• Deep understanding of AI inference systems and GPU-backed infrastructure, with strong knowledge of performance-sensitive environments.


• Hands-on experience working with LLM workloads and the architectural trade-offs involved in deploying inference systems at scale.


• Practical experience with inference frameworks and libraries such as vLLM, SGLang, or TensorRT-LLM.


• Strong ability to reason about latency, throughput, cost, scalability, resource utilization, and overall architecture trade-offs.


• Experience working directly with engineering-led organizations, technical founders, developers, or highly technical customer teams.


• Strong customer-facing and communication skills, with the confidence to challenge assumptions and push back constructively when necessary.


• Commercial awareness and an understanding that engineering capacity is a strategic resource that must be allocated thoughtfully.


• Strong Python skills and familiarity with modern AI, API, MLOps, DevOps, and cloud technologies.


• Experience with technologies such as OpenAI or Anthropic SDKs, LangChain, LangSmith, smolagents, FastAPI, Flask, Kubernetes, Docker, and Git is highly valuable.


• Familiarity with major cloud AI platforms such as AWS SageMaker and Bedrock, Google Cloud Vertex AI, or Azure Machine Learning is preferred.


• Ability to operate effectively in a fast-moving, international environment with a high degree of ownership and autonomy.

• Competitive compensation.


• Flexible remote work opportunities within Europe.


• High level of ownership, autonomy, and flexibility.


• Career growth and continuous learning opportunities.


• Opportunity to work on impactful, technically challenging AI infrastructure projects.


• Collaborative, innovative, and engineering-driven working environment.


• International team with highly experienced professionals across AI, software, and infrastructure.


• Opportunity to influence platform evolution and shape solutions for real-world AI workloads.


• Fast-paced environment with meaningful impact and significant opportunities for professional growth.

Deze vacature komt van Lever. Originele vacature bekijken ↗