[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"seo-content-skill-vllm-global":3,"job-search-\u002Fde-global\u002Fjobs-by-skill\u002Fvllm":4,"skill-page-filters-\u002Fde-global\u002Fjobs-by-skill\u002Fvllm":272,"featured-jobs-\u002Fde-global\u002Fjobs-by-skill\u002Fvllm":410},{},{"total":5,"jobs":6},6,[7,60,127,177,195,218],{"id":8,"slug":9,"title":10,"raw_title":11,"is_featured":12,"company":13,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":16,"processed_country_iso_code_gmaps":17,"processed_home_office":19,"processed_salary_min":20,"processed_salary_max":21,"processed_salary_currency":22,"processed_salary_source":23,"processed_working_hours":24,"processed_employment_types":26,"processed_it_skills":27,"processed_it_skills_labels":31,"processed_job_expertise_skills":49,"processed_job_expertise_skills_labels":50,"max_cpc":59,"actual_cpc":59},88918,"manager-genai-l3-support-engineer-group-technology-ops-united-overseas-bank-ltd","Manager, GenAI L3 Support Engineer, Group Technology & Ops",null,false,{"name":14,"slug":15,"logo_url":11},"United Overseas Bank Ltd","united-overseas-bank-ltd",[],[18],"SG","onsite",90000,150000,"SGD","estimated",[25],"FULL_TIME","permanent",{"git":28,"vllm":29,"flask":28,"redis":30,"python":30,"fastapi":28,"grafana":28,"jenkins":28,"langchain":30,"openshift":29,"kubernetes":29,"llamaguard":28,"prometheus":28,"elasticsearch":30,"guardrails ai":28,"opentelemetry":28,"nvidia enterprise ai":29},3,2,4,[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"Python","LangChain","Elasticsearch","Redis","Guardrails AI","LlamaGuard","Jenkins","Prometheus","Grafana","OpenTelemetry","Git","Kubernetes","OpenShift","vLLM","NVIDIA Enterprise AI","FastAPI","Flask",{"ci\u002Fcd":28,"openshift":29,"kubernetes":29,"llm serving":29,"data handling":28,"observability":28,"security practices":28,"incident management":30,"root cause analysis":30,"site reliability engineering":30},[51,52,53,54,55,56,57,43,44,58],"Site Reliability Engineering","Incident Management","Root Cause Analysis","CI\u002FCD","Observability","Data Handling","Security Practices","LLM Serving",1,{"id":61,"slug":62,"title":63,"raw_title":11,"is_featured":12,"company":64,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":68,"processed_country_iso_code_gmaps":70,"processed_home_office":72,"processed_salary_min":73,"processed_salary_max":20,"processed_salary_currency":74,"processed_salary_source":23,"processed_working_hours":75,"processed_employment_types":26,"processed_it_skills":76,"processed_it_skills_labels":77,"processed_job_expertise_skills":106,"processed_job_expertise_skills_labels":107,"max_cpc":59,"actual_cpc":59},87110,"santander-ai-lab-frontier-agentic-ai-engineer-banco-santander-sa","Santander AI Lab - Frontier Agentic AI Engineer",{"name":65,"slug":66,"logo_url":67},"Banco Santander S.A.","banco-santander-sa","\u002Fimages\u002Flogos\u002Fsantander-logo-2018.svg",[69],"Madrid",[71],"ES","hybrid",60000,"EUR",[25],{"ap2":28,"git":30,"vllm":28,"x402":28,"llama":28,"ragas":30,"aws s3":30,"crewai":30,"docker":30,"ollama":28,"python":30,"autogen":30,"fastapi":30,"mistral":28,"unsloth":28,"graphrag":28,"langfuse":30,"langgraph":30,"promptfoo":30,"rest apis":30,"terraform":28,"aws lambda":30,"kubernetes":28,"openai api":30,"aws bedrock":30,"a2a protocol":28,"llm-as-judge":30,"aws sagemaker":30,"ci\u002Fcd pipelines":30,"semantic kernel":30,"knowledge graphs":28,"anthropic claude api":30,"mcp (model context protocol)":28},[32,78,79,80,81,82,83,84,85,86,87,88,89,47,90,42,91,92,45,93,94,95,96,97,98,99,43,100,101,102,103,104,105],"LangGraph","AutoGen","CrewAI","Semantic Kernel","Anthropic Claude API","OpenAI API","Llama","Mistral","AWS Bedrock","AWS Lambda","AWS SageMaker","AWS S3","Docker","CI\u002FCD pipelines","MCP (Model Context Protocol)","Ollama","Unsloth","Knowledge graphs","GraphRAG","A2A protocol","x402","AP2","Terraform","REST APIs","LLM-as-judge","RAGAS","Promptfoo","Langfuse",{"devops basics":30,"api development":30,"kubernetes, terraform":28,"spec-driven development":28,"a2a protocol, x402 or ap2":28,"slm fine-tuning pipelines":28,"knowledge graphs or graphrag":28,"multi-agent ai systems design":30,"building and consuming rest apis":30,"harness engineering methodologies":28,"llm-powered systems in production":30,"model evaluation and observability":30,"mcp server design and implementation":28,"ai-assisted software creation at scale":28,"dataset curation and evaluation design":30,"delivering complete systems independently":30,"banking\u002Ffintech\u002Fregulated industry experience":28,"fine-tuning language models (sft, lora, rlhf)":30,"integrating ai systems with enterprise data sources":30},[108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126],"Multi-agent AI systems design","LLM-powered systems in production","Fine-tuning language models (SFT, LoRA, RLHF)","Dataset curation and evaluation design","Delivering complete systems independently","Building and consuming REST APIs","Integrating AI systems with enterprise data sources","Banking\u002Ffintech\u002Fregulated industry experience","Harness Engineering methodologies","Spec-driven development","AI-assisted software creation at scale","Model evaluation and observability","API development","DevOps basics","MCP server design and implementation","SLM fine-tuning pipelines","Knowledge graphs or GraphRAG","A2A protocol, x402 or AP2","Kubernetes, Terraform",{"id":128,"slug":129,"title":130,"raw_title":11,"is_featured":12,"company":131,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":134,"processed_country_iso_code_gmaps":136,"processed_home_office":72,"processed_salary_min":138,"processed_salary_max":139,"processed_salary_currency":140,"processed_salary_source":23,"processed_working_hours":141,"processed_employment_types":26,"processed_it_skills":142,"processed_it_skills_labels":143,"processed_job_expertise_skills":162,"processed_job_expertise_skills_labels":163,"max_cpc":59,"actual_cpc":59},81099,"principal-cloud-engineer-ai-bank-of-montreal","Principal Cloud Engineer AI",{"name":132,"slug":133,"logo_url":11},"Bank of Montreal","bank-of-montreal",[135],"Chicago",[137],"US",120000,250000,"USD",[25],{"go":28,"aws":30,"cuda":29,"vllm":28,"azure":30,"bicep":28,"ci\u002Fcd":30,"faiss":28,"kafka":28,"docker":30,"gitops":28,"kserve":28,"milvus":28,"mlflow":28,"python":30,"triton":28,"grafana":28,"azure ml":28,"pgvector":28,"pinecone":28,"terraform":30,"kubernetes":30,"prometheus":28,"typescript":28,"hugging face":28,"tensorrt-llm":29,"opentelemetry":28},[32,144,145,43,100,146,147,148,54,149,90,150,39,40,41,151,152,45,153,154,155,156,157,158,159,160,161],"Go","TypeScript","Bicep","Azure","AWS","GitOps","Kafka","CUDA","TensorRT-LLM","Triton","KServe","FAISS","Milvus","Pinecone","pgvector","Azure ML","MLflow","Hugging Face",{"mlops":30,"finops":28,"llmops":30,"security":30,"networking":30,"observability":30,"responsible ai":28,"data governance":28,"ai\u002Fml infrastructure":30,"cloud infrastructure":30,"technical leadership":30,"solution architecture":30,"infrastructure as code":30,"container orchestration":30,"site reliability engineering":30},[164,165,166,167,168,169,170,171,55,172,51,173,174,175,176],"Cloud Infrastructure","AI\u002FML Infrastructure","MLOps","LLMOps","Infrastructure as Code","Container Orchestration","Networking","Security","FinOps","Solution Architecture","Technical Leadership","Responsible AI","Data Governance",{"id":178,"slug":179,"title":180,"raw_title":11,"is_featured":12,"company":181,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":182,"processed_country_iso_code_gmaps":184,"processed_home_office":72,"processed_salary_min":186,"processed_salary_max":187,"processed_salary_currency":140,"processed_salary_source":23,"processed_working_hours":188,"processed_employment_types":26,"processed_it_skills":189,"processed_it_skills_labels":190,"processed_job_expertise_skills":192,"processed_job_expertise_skills_labels":193,"max_cpc":59,"actual_cpc":59},81393,"principal-ai-cloud-engineer-bank-of-montreal","Principal AI Cloud Engineer",{"name":132,"slug":133,"logo_url":11},[183],"Toronto",[185],"CA",105000,215000,[25],{"go":28,"aws":30,"sql":28,"cuda":29,"vllm":28,"azure":30,"bicep":28,"ci\u002Fcd":30,"faiss":28,"kafka":28,"docker":30,"gitops":28,"kserve":28,"milvus":28,"mlflow":28,"python":30,"triton":28,"grafana":28,"azure ml":28,"pgvector":28,"pinecone":28,"terraform":30,"kubernetes":30,"prometheus":28,"typescript":28,"hugging face":28,"tensorrt-llm":29,"opentelemetry":28},[32,144,145,43,100,146,147,148,54,149,90,150,39,40,41,151,152,45,153,154,160,159,161,155,156,157,158,191],"SQL",{"mlops":30,"finops":28,"llmops":30,"security":30,"networking":30,"observability":30,"responsible ai":28,"sre principles":28,"data governance":28,"ai\u002Fml infrastructure":30,"cloud infrastructure":30,"technical leadership":30,"solution architecture":30},[164,165,166,167,171,170,55,172,194,173,174,175,176],"SRE Principles",{"id":196,"slug":197,"title":198,"raw_title":11,"is_featured":12,"company":199,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":200,"processed_country_iso_code_gmaps":202,"processed_home_office":19,"processed_salary_min":138,"processed_salary_max":203,"processed_salary_currency":22,"processed_salary_source":23,"processed_working_hours":204,"processed_employment_types":26,"processed_it_skills":205,"processed_it_skills_labels":206,"processed_job_expertise_skills":210,"processed_job_expertise_skills_labels":211,"max_cpc":59,"actual_cpc":59},68081,"vp1-senior-genai-engineer-gmet-1011-united-overseas-bank-ltd","VP1 Senior GenAI Engineer, GMET",{"name":14,"slug":15,"logo_url":11},[201],"Singapore",[18],180000,[25],{"rag":30,"java":28,"vllm":28,"redis":28,"python":30,"elastic":28,"langfuse":28,"langchain":30,"langgraph":30,"openshift":28,"kubernetes":28},[32,207,78,33,208,43,44,35,45,209,105],"Java","RAG","Elastic",{"api design":28,"observability":28,"troubleshooting":28,"distributed systems":28,"software engineering":30,"production resilience":28,"enterprise integration":30},[212,213,214,215,55,216,217],"Software Engineering","API Design","Distributed Systems","Production Resilience","Troubleshooting","Enterprise Integration",{"id":219,"slug":220,"title":221,"raw_title":11,"is_featured":12,"company":222,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":225,"processed_country_iso_code_gmaps":226,"processed_home_office":19,"processed_salary_min":138,"processed_salary_max":203,"processed_salary_currency":22,"processed_salary_source":23,"processed_working_hours":227,"processed_employment_types":26,"processed_it_skills":228,"processed_it_skills_labels":229,"processed_job_expertise_skills":252,"processed_job_expertise_skills_labels":253,"max_cpc":59,"actual_cpc":271},62347,"data-scientist-platform-ai-squad-group-data-office-avpvp-ocbc-bank","Data Scientist, Platform AI Squad, Group Data Office (AVP\u002FVP)",{"name":223,"slug":224,"logo_url":11},"OCBC Bank","ocbc-bank",[],[18],[25],{"s3":30,"a2a":30,"aws":30,"ec2":30,"eks":30,"git":30,"iam":30,"mcp":30,"ray":30,"grpc":30,"helm":30,"rest":30,"vllm":30,"ragas":30,"argocd":30,"docker":30,"mlflow":30,"python":30,"triton":30,"grafana":30,"jenkins":30,"deepeval":30,"bitbucket":30,"gitlab ci":30,"langchain":30,"langgraph":30,"terraform":30,"cloudwatch":30,"kubernetes":30,"llamaindex":30,"prometheus":30,"privatelink":30,"tensorrt-llm":30,"amazon bedrock":30,"github actions":30,"amazon sagemaker":30,"aws codepipeline":30,"bedrock guardrails":30},[32,148,90,43,100,230,42,160,33,78,231,45,152,153,232,233,234,235,38,236,237,238,239,240,241,242,243,244,245,39,40,103,246,247,248,249,250,251],"Helm","LlamaIndex","Ray","GitHub Actions","GitLab CI","Bitbucket","AWS CodePipeline","ArgoCD","Amazon Bedrock","Amazon SageMaker","EKS","EC2","S3","IAM","CloudWatch","PrivateLink","DeepEval","Bedrock Guardrails","MCP","A2A","REST","gRPC",{"ci\u002Fcd":30,"mlops":30,"devops":30,"microservices":30,"pagedattention":30,"dynamic batching":30,"model versioning":30,"high availability":30,"metadata tracking":30,"cloud architecture":30,"incident resolution":30,"kv cache offloading":30,"speculative decoding":30,"gpu capacity planning":30,"quantization techniques":30,"telemetry configuration":30,"multi-agent orchestration":30,"llm inference optimization":30,"model lifecycle management":30},[254,166,255,256,257,258,259,54,260,261,262,263,264,265,266,267,268,269,270],"LLM Inference Optimization","DevOps","Cloud Architecture","Multi-agent Orchestration","Model Lifecycle Management","GPU Capacity Planning","Microservices","Quantization Techniques","PagedAttention","Dynamic Batching","KV Cache Offloading","Speculative Decoding","Model Versioning","Metadata Tracking","Telemetry Configuration","Incident Resolution","High Availability",0.5,{"industry":273,"employment_type":281,"expertise_skills":284,"it_skills":346,"salary_currency":404,"processed_working_hours":408},[274,278],{"key":275,"label":276,"count":277},"banking","Banking",5,{"key":279,"label":280,"count":277},"financial services","Financial Services",[282],{"key":26,"label":283,"count":5},"PERMANENT",[285,287,290,293,295,297,299,301,304,306,308,311,314,317,319,322,324,327,330,333,335,338,341,343],{"key":286,"label":55,"slug":286,"count":30},"observability",{"key":288,"label":289,"slug":288,"count":28},"mlops","Mlops",{"key":291,"label":292,"slug":291,"count":29},"responsible-ai","Responsible Ai",{"key":294,"label":170,"slug":294,"count":29},"networking",{"key":296,"label":174,"slug":296,"count":29},"technical-leadership",{"key":298,"label":51,"slug":298,"count":29},"site-reliability-engineering",{"key":300,"label":171,"slug":300,"count":29},"security",{"key":302,"label":303,"slug":302,"count":29},"llmops","Llmops",{"key":305,"label":173,"slug":305,"count":29},"solution-architecture",{"key":307,"label":164,"slug":307,"count":29},"cloud-infrastructure",{"key":309,"label":310,"slug":309,"count":29},"finops","Finops",{"key":312,"label":313,"slug":312,"count":29},"aiml-infrastructure","Ai\u002FMl Infrastructure",{"key":315,"label":316,"slug":315,"count":29},"cicd","Ci\u002FCd",{"key":318,"label":176,"slug":318,"count":29},"data-governance",{"key":320,"label":321,"slug":320,"count":59},"llm-serving","Llm Serving",{"key":323,"label":216,"slug":323,"count":59},"troubleshooting",{"key":325,"label":326,"slug":325,"count":59},"delivering-complete-systems-independently","Delivering Complete Systems Independently",{"key":328,"label":329,"slug":328,"count":59},"bankingfintechregulated-industry-experience","Banking\u002FFintech\u002FRegulated Industry Experience",{"key":331,"label":332,"slug":331,"count":59},"gpu-capacity-planning","Gpu Capacity Planning",{"key":334,"label":43,"slug":334,"count":59},"kubernetes",{"key":336,"label":337,"slug":336,"count":59},"mcp-server-design-and-implementation","Mcp Server Design And Implementation",{"key":339,"label":340,"slug":339,"count":59},"knowledge-graphs-or-graphrag","Knowledge Graphs Or Graphrag",{"key":342,"label":215,"slug":342,"count":59},"production-resilience",{"key":344,"label":345,"slug":344,"count":59},"devops-basics","Devops Basics",[347,349,352,353,355,357,359,361,364,366,369,371,374,377,380,383,386,388,390,393,395,398,401,402],{"key":348,"label":32,"slug":348,"count":5},"python",{"key":350,"label":351,"slug":350,"count":5},"vllm","Vllm",{"key":334,"label":43,"slug":334,"count":5},{"key":354,"label":39,"slug":354,"count":30},"prometheus",{"key":356,"label":100,"slug":356,"count":30},"terraform",{"key":358,"label":40,"slug":358,"count":30},"grafana",{"key":360,"label":90,"slug":360,"count":30},"docker",{"key":362,"label":363,"slug":362,"count":28},"tensorrt-llm","Tensorrt-Llm",{"key":365,"label":153,"slug":365,"count":28},"triton",{"key":367,"label":368,"slug":367,"count":28},"langchain","Langchain",{"key":370,"label":42,"slug":370,"count":28},"git",{"key":372,"label":373,"slug":372,"count":28},"langgraph","Langgraph",{"key":375,"label":376,"slug":375,"count":28},"mlflow","Mlflow",{"key":378,"label":379,"slug":378,"count":28},"opentelemetry","Opentelemetry",{"key":381,"label":382,"slug":381,"count":28},"aws","Aws",{"key":384,"label":385,"slug":384,"count":29},"gitops","Gitops",{"key":387,"label":146,"slug":387,"count":29},"bicep",{"key":389,"label":35,"slug":389,"count":29},"redis",{"key":391,"label":392,"slug":391,"count":29},"azure-ml","Azure Ml",{"key":394,"label":38,"slug":394,"count":29},"jenkins",{"key":396,"label":397,"slug":396,"count":29},"faiss","Faiss",{"key":399,"label":400,"slug":399,"count":29},"fastapi","Fastapi",{"key":315,"label":316,"slug":315,"count":29},{"key":403,"label":156,"slug":403,"count":29},"milvus",[405,406,407],{"key":22,"label":22,"count":28},{"key":140,"label":140,"count":29},{"key":74,"label":74,"count":59},[409],{"key":25,"label":25,"count":5},{"total":59,"jobs":411},[412],{"id":413,"slug":414,"title":415,"raw_title":11,"is_featured":416,"company":417,"raw_hiringOrganization_logo_url":11,"processed_city_gmaps":421,"processed_country_iso_code_gmaps":423,"processed_home_office":425,"processed_salary_min":426,"processed_salary_max":427,"processed_salary_currency":74,"processed_salary_source":11,"processed_working_hours":428,"processed_employment_types":283,"processed_it_skills":430,"processed_it_skills_labels":11,"processed_job_expertise_skills":431,"processed_job_expertise_skills_labels":432,"max_cpc":439,"actual_cpc":11},52265,"privatkundenbetreuer-mwd-banking-frankfurt-am-main-white-horse-international-gmbh","Privatkundenbetreuer (m\u002Fw\u002Fd) – Banking | Frankfurt am Main",true,{"name":418,"slug":419,"logo_url":420},"White Horse International GmbH","white-horse-international-gmbh","https:\u002F\u002Fwhitehorse-international.com\u002Fwp-content\u002Fuploads\u002F2022\u002F03\u002Fwhite-horse-logo-final-gif.gif",[422],"Frankfurt am Main",[424],"DE","HYBRID",45000,65000,[429],"full_time",{},{"Financial Analysis":28,"Regulatory Compliance":28,"New Customer Acquisition":28,"Private Banking Advisory":28,"Banking Products Knowledge":28,"Customer Relationship Management":28},[433,434,435,436,437,438],"Private Banking Advisory","Financial Analysis","Banking Products Knowledge","Regulatory Compliance","Customer Relationship Management","New Customer Acquisition",0.8]