AI Infrastructure Architect
<p><b>Salary: £50,000 - 90,000 per year</b></p>
<b>Requirements:</b>
<ul><li>Strong foundational knowledge in system architecture or computer architecture, operating systems, and runtime environments</li><li>Hands-on experience with Serverless architectures and cloud-native optimization technologies such as containers, Kubernetes, service orchestration, and autoscaling</li><li>Familiarity with vLLM, SGLang, Ray Serve, etc.</li><li>Understanding of common optimization concepts such as continuous batching, KV-Cache reuse, parallelism, and compression/quantization/distillation</li><li>Proficient in using Profiling/Tracing tools</li><li>Experienced in analyzing and optimizing system-level bottlenecks regarding GPU utilization, memory/bandwidth, Interconnect Fabric, and network/storage paths</li><li>Proficient in at least one system-level language (e.g., C/C++, Go, Rust)</li><li>Proficient in one scripting language (e.g., Python)</li></ul>
<b>Responsibilities:</b>
<ul><li>Design a unified AI Infra & Serving architecture platform for composite AI workloads such as LLM Training & Inference, RLHF, Agent, and Multimodal processing</li><li>Integrate inference, orchestration, and state management, defining the technical evolution path for Serverless AI Agentic Serving</li><li>Design a heterogeneous execution framework across CPU/GPU/NPU for agent memory, tool invocation, and long-running multi-turn conversations and tasks</li><li>Build an efficient memory/KV-cache/vector store/logging and state-management subsystem to support agent retrieval, planning, and persistent memory</li><li>Build a high-performance Runtime/Framework that defines the next-generation Serverless AI foundation through elastic scaling, cold start optimization, batch processing, function-based inference, request orchestration, dynamic decoupled deployment, and other features to support performance scenarios such as multiple models, multi-tenancy, and high concurrency</li></ul>
<b>Technologies:</b>
<ul><li>AI</li><li>Cloud</li><li>Fabric</li><li>Support</li><li>Kubernetes</li><li>LLM</li><li>Network</li><li>Python</li><li>Rust</li><li>Serverless</li><li>Architect</li></ul>
<p><b>More:</b></p>
<p>We are a leading tech company committed to innovation in artificial intelligence. Our team is dedicated to creating advanced solutions that push the boundaries of technology, and we offer a collaborative work environment that encourages creativity and growth. We provide competitive benefits, including flexible working arrangements and professional development opportunities. Join us as we build the future of AI in a dynamic and exciting location.</p>
<p>last updated 8 week of 2026</p>
<b>Requirements:</b>
<ul><li>Strong foundational knowledge in system architecture or computer architecture, operating systems, and runtime environments</li><li>Hands-on experience with Serverless architectures and cloud-native optimization technologies such as containers, Kubernetes, service orchestration, and autoscaling</li><li>Familiarity with vLLM, SGLang, Ray Serve, etc.</li><li>Understanding of common optimization concepts such as continuous batching, KV-Cache reuse, parallelism, and compression/quantization/distillation</li><li>Proficient in using Profiling/Tracing tools</li><li>Experienced in analyzing and optimizing system-level bottlenecks regarding GPU utilization, memory/bandwidth, Interconnect Fabric, and network/storage paths</li><li>Proficient in at least one system-level language (e.g., C/C++, Go, Rust)</li><li>Proficient in one scripting language (e.g., Python)</li></ul>
<b>Responsibilities:</b>
<ul><li>Design a unified AI Infra & Serving architecture platform for composite AI workloads such as LLM Training & Inference, RLHF, Agent, and Multimodal processing</li><li>Integrate inference, orchestration, and state management, defining the technical evolution path for Serverless AI Agentic Serving</li><li>Design a heterogeneous execution framework across CPU/GPU/NPU for agent memory, tool invocation, and long-running multi-turn conversations and tasks</li><li>Build an efficient memory/KV-cache/vector store/logging and state-management subsystem to support agent retrieval, planning, and persistent memory</li><li>Build a high-performance Runtime/Framework that defines the next-generation Serverless AI foundation through elastic scaling, cold start optimization, batch processing, function-based inference, request orchestration, dynamic decoupled deployment, and other features to support performance scenarios such as multiple models, multi-tenancy, and high concurrency</li></ul>
<b>Technologies:</b>
<ul><li>AI</li><li>Cloud</li><li>Fabric</li><li>Support</li><li>Kubernetes</li><li>LLM</li><li>Network</li><li>Python</li><li>Rust</li><li>Serverless</li><li>Architect</li></ul>
<p><b>More:</b></p>
<p>We are a leading tech company committed to innovation in artificial intelligence. Our team is dedicated to creating advanced solutions that push the boundaries of technology, and we offer a collaborative work environment that encourages creativity and growth. We provide competitive benefits, including flexible working arrangements and professional development opportunities. Join us as we build the future of AI in a dynamic and exciting location.</p>
<p>last updated 8 week of 2026</p>