Buscar empleo: 64 ofertas de trabajo de chat en Santander (septiembre 2026)

Cloud Platform Engineer (Agentic Ai)

hace 1 día

Santander

The project is for one of the world's famous science and technology companies in pharmaceutical industry, supporting initiatives in AWS, AI and data engineering, with plans to launch over 20 additional initiatives in the future. We are seeking a highly skilled Cloud Engineer to lead the infrastructure design, deployment, and operations of the AI agent orchestration platform on AWS. This role is responsible for building and managing a Kubernetes-native, enterprise-grade platform that supports scalable AI agent workloads across development, QA, and production environments. • Design, provision, and manage AWS infrastructure using Terraform, aligned with the AWS Well-Architected Framework. Core services include: Amazon EKS VPC IAM Route 53 Own and operate EKS clusters end-to‑end Managed node group lifecycle management: Karpenter-based autoscaling Cluster add‑on lifecycle upgrades IRSA (IAM Roles for Service Accounts) configuration Multi-AZ high availability and resilience CI/CD & GitOps Build and maintain automated deployment pipelines using: GitHub Actions ArgoCD (GitOps) Implement release strategies: Canary releases Security & Compliance Integrate AWS-native security and governance controls: AWS WAF GuardDuty Security Hub KMS (encryption) Secrets Manager External Secrets Operator Enforce policy controls using: Observability & Monitoring Implement and manage observability stack: Amazon Managed Prometheus Amazon Managed Grafana CloudWatch Container Insights AWS X‑Ray (distributed tracing) AI/ML Integration Leverage AWS AI/ML services to support agent orchestration: Cost Optimization (FinOps) Spot Instances Savings Plans Karpenter bin‑packing strategies Scheduled scale‑to‑zero for non‑production environments Platform & Engineering Collaboration Partner with platform and ML teams to: Integrate MCP servers and execution frameworks Support extensibility of the agent ecosystem 4+ years of hands‑on AWS experience AWS Certifications: Required: AWS Solutions Architect (Associate or Professional) Preferred: DevOps Engineer, Security Specialty Kubernetes & EKS Expertise Strong hands‑on experience with: EKS cluster provisioning and operations Managed node groups and Karpenter Kubernetes RBAC and network policies Infrastructure as Code (Terraform) Advanced Terraform capabilities: Remote state management (S3 + DynamoDB) Security scanning (Checkov, tfsec) AWS Services Proficiency Deep knowledge of: EKS, ECR, ALB, Route 53, ACM IAM, KMS, Secrets Manager IAM Identity Center CloudTrail, AWS Config GuardDuty, Security Hub, AWS WAF AI/ML Exposure Practical experience with: SageMaker (model deployment and endpoints) Comprehend (NLP and PII detection) DevOps & Identity Experience with: GitOps tools (ArgoCD or Flux) CI/CD pipelines for container workloads GitHub Actions → AWS EKS OIDC provider integration Observability & Debugging Familiarity with: OpenTelemetry AWS X‑Ray Strong understanding of: Pod Security Standards Admission webhooks Service account least‑privilege principles Experience with AI agent frameworks: LangChain, Claude Agent SDK, or similar Knowledge of emerging protocols: A2A (Agent‑to‑Agent) Familiarity with: Amazon Bedrock Agents, Knowledge Bases, Guardrails Namespace isolation Programming/debugging skills: Python, Go, or Node.js AWS Cost Explorer The project is for one of the world's famous science and technology companies in pharmaceutical industry, supporting initiatives in AWS, AI and data engineering, with plans to launch over 20 additional initiatives in the future. We are seeking a highly skilled Cloud Engineer to lead the infrastructure design, deployment, and operations of the AI agent orchestration platform on AWS. This role is responsible for building and managing a Kubernetes-native, enterprise-grade platform that supports scalable AI agent workloads across development, QA, and production environments. • Design, provision, and manage AWS infrastructure using Terraform, aligned with the AWS Well-Architected Framework. Core services include: Amazon EKS VPC IAM Route 53 Own and operate EKS clusters end‑to‑end Managed node group lifecycle management: Karpenter-based autoscaling Cluster add‑on lifecycle upgrades IRSA (IAM Roles for Service Accounts) configuration Multi-AZ high availability and resilience CI/CD & GitOps Build and maintain automated deployment pipelines using: GitHub Actions ArgoCD (GitOps) Implement release strategies: Canary releases Security & Compliance Integrate AWS-native security and governance controls: AWS WAF GuardDuty Security Hub KMS (encryption) Secrets Manager External Secrets Operator Enforce policy controls using: Observability & Monitoring Implement and manage observability stack: Amazon Managed Prometheus Amazon Managed Grafana CloudWatch Container Insights AWS X‑Ray (distributed tracing) AI/ML Integration Leverage AWS AI/ML services to support agent orchestration: Cost Optimization (FinOps) Spot Instances Savings Plans Karpenter bin‑packing strategies Scheduled scale‑to‑zero for non‑production environments Platform & Engineering Collaboration Partner with platform and ML teams to: Integrate MCP servers and execution frameworks Support extensibility of the agent ecosystem 4+ years of hands‑on AWS experience AWS Certifications: Required: AWS Solutions Architect (Associate or Professional) Preferred: DevOps Engineer, Security Specialty Kubernetes & EKS Expertise Strong hands‑on experience with: EKS cluster provisioning and operations Managed node groups and Karpenter Kubernetes RBAC and network policies Infrastructure as Code (Terraform) Advanced Terraform capabilities: Remote state management (S3 + DynamoDB) Security scanning (Checkov, tfsec) AWS Services Proficiency Deep knowledge of: EKS, ECR, ALB, Route 53, ACM IAM, KMS, Secrets Manager IAM Identity Center CloudTrail, AWS Config GuardDuty, Security Hub, AWS WAF AI/ML Exposure Practical experience with: SageMaker (model deployment and endpoints) Comprehend (NLP and PII detection) DevOps & Identity Experience with: GitOps tools (ArgoCD or Flux) CI/CD pipelines for container workloads GitHub Actions → AWS EKS OIDC provider integration Observability & Debugging Familiarity with: OpenTelemetry AWS X‑Ray Strong understanding of: Pod Security Standards Admission webhooks Service account least‑privilege principles Experience with AI agent frameworks: LangChain, Claude Agent SDK, or similar Knowledge of emerging protocols: A2A (Agent‑to‑Agent) Familiarity with: Amazon Bedrock Agents, Knowledge Bases, Guardrails Namespace isolation Programming/debugging skills: Python, Go, or Node.js AWS Cost Explorer Hoy • GKE, • AlloyDB FirstIgnite makes software for university tech transfer offices. Those are the people who take research coming out of a university lab and get it patented, licensed, or spun out into a company. We're hiring a Senior AI Agent Engineer. You'll build the agents in our product, and you'll build the evals that tell us whether each change made them better or worse. The work is document-heavy rather than chat. The agents run multi-step, call tools, read long and inconsistently formatted source material, check it against existing records, and produce output that a person reviews before anything happens with it. Accuracy matters more here than speed or novelty. Most of the engineering effort goes into precision, traceability, and getting the agent to hand off to a human at the right moment. You'll report to the Head of Engineering and work with product and the full-stack team. If you've shipped agents before, you've probably had the experience of changing a prompt and having no idea whether you improved anything. That problem is most of this job. Design and ship long-running, multi-step, tool-using agents on various AI SDKs and tooling, included but not limited to the OpenAI Agents SDK, the Anthropic Agent SDK, the Vercel AI SDK, LangGraph, MCP, and Temporal Cloud. Wrap our APIs and our partners' APIs as tools an agent can call over MCP. Some of those systems are old, single-tenant, and outside our control, so a fair amount of the work is translation. Get structured data out of long documents and match it against records that already exist. Expect entity resolution and fuzzy matching, and expect much of it to run in batch. Stand up eval suites using various evaluation frameworks and tooling, included but not limited to Promptfoo, Braintrust, LangSmith, DeepEval, LLM-as-judge methods, and custom harnesses. Measure tool-use correctness, trajectory quality, and whether the agent finished the task. Every agent here produces a draft that a person signs off on. Build the citations and confidence signals that make that review fast, and give the agent a clear way to elevate. Sit with product and domain experts and turn vague quality goals into something measurable. Sometimes the only dataset available for that is tiny, or confidential, or both. Instrument production traffic, turn real customer interactions into golden datasets, and run them as regression tests. Compare models against each other (OpenAI, Anthropic, open-weight), along with prompt strategies and agent designs, and know what each option costs in latency and quality. Bootstrap quality signal for features that have no production traffic yet. That usually means generating synthetic documents and test cases, including the ugly edge cases real customers will eventually send us, and knowing where synthetic data stops being a good proxy. Write the templates, docs, and tooling the rest of the team needs to run evals without coming to you. 3+ years of engineering experience, including hands-on work on LLM or agent systems that real users touched. You've evaluated agents, not only models, and you know why single-turn accuracy says little about a multi-step run. You've integrated against APIs you don't own, including old ones with bad documentation, and turned them into something an agent can call reliably. You're comfortable with document pipelines: pulling data out, normalizing it, and checking it against a structured source of truth. You've used at least one LLM evaluation framework, in-house tooling included. You know how LLM-as-judge methods break down (position bias, verbosity bias, judge drift) and what to do about it. You can tell a real regression from noise, and design an experiment that answers the question being asked instead of a nearby one. You can read a customer call transcript, work out which failures matter, and ship a fix and an eval for them. You write clearly. Engineers won't act on eval results they don't read or don't trust. You're based somewhere between New York time (ET) and Western European time. Italy is the furthest east we can go. You might currently be titled Titles are all over the place in this space. If the work above matches what you already do, apply. We'll go on what you've shipped. You've evaluated retrieval systems: RAG, hybrid search, reranking. You've worked with agent orchestration frameworks like Temporal, LangGraph, or the OpenAI Agents SDK, and you know how long-running tool use goes wrong. You have a background in information retrieval or search relevance. You've worked somewhere an agent's output carried financial or compliance consequences. You've built internal tooling that non-engineers used on their own to label and review model output. This is a fully remote, full-time permanent position available to candidates located within the New York (ET) through Western Europe time zones, with flexible working hours to support collaboration across regions. We're hiring a Senior AI Agent Engineer. You'll build the agents in our product, and you'll build the evals that tell us whether each change made them better or worse. The work is document-heavy rather than chat. The agents run multi-step, call tools, read long and inconsistently formatted source material, check it against existing records, and produce output that a person reviews before anything happens with it. Accuracy matters more here than speed or novelty. Most of the engineering effort goes into precision, traceability, and getting the agent to hand off to a human at the right moment. You'll report to the Head of Engineering and work with product and the full-stack team. If you've shipped agents before, you've probably had the experience of changing a prompt and having no idea whether you improved anything. That problem is most of this job. Design and ship long-running, multi-step, tool-using agents on various AI SDKs and tooling, included but not limited to the OpenAI Agents SDK, the Anthropic Agent SDK, the Vercel AI SDK, LangGraph, MCP, and Temporal Cloud. Wrap our APIs and our partners' APIs as tools an agent can call over MCP. Some of those systems are old, single-tenant, and outside our control, so a fair amount of the work is translation. Get structured data out of long documents and match it against records that already exist. Expect entity resolution and fuzzy matching, and expect much of it to run in batch. Stand up eval suites using various evaluation frameworks and tooling, included but not limited to Promptfoo, Braintrust, LangSmith, DeepEval, LLM-as-judge methods, and custom harnesses. Measure tool-use correctness, trajectory quality, and whether the agent finished the task. Every agent here produces a draft that a person signs off on. Build the citations and confidence signals that make that review fast, and give the agent a clear way to elevate. Sit with product and domain experts and turn vague quality goals into something measurable. Sometimes the only dataset available for that is tiny, or confidential, or both. Instrument production traffic, turn real customer interactions into golden datasets, and run them as regression tests. Compare models against each other (OpenAI, Anthropic, open-weight), along with prompt strategies and agent designs, and know what each option costs in latency and quality. Bootstrap quality signal for features that have no production traffic yet. That usually means generating synthetic documents and test cases, including the ugly edge cases real customers will eventually send us, and knowing where synthetic data stops being a good proxy. Write the templates, docs, and tooling the rest of the team needs to run evals without coming to you. 3+ years of engineering experience, including hands-on work on LLM or agent systems that real users touched. You've evaluated agents, not only models, and you know why single-turn accuracy says little about a multi-step run. You've integrated against APIs you don't own, including old ones with bad documentation, and turned them into something an agent can call reliably. You're comfortable with document pipelines: pulling data out, normalizing it, and checking it against a structured source of truth. You've used at least one LLM evaluation framework, in-house tooling included. You know how LLM-as-judge methods break down (position bias, verbosity bias, judge drift) and what to do about it. You can tell a real regression from noise, and design an experiment that answers the question being asked instead of a nearby one. You can read a customer call transcript, work out which failures matter, and ship a fix and an eval for them. You write clearly. Engineers won't act on eval results they don't read or don't trust. You're based somewhere between New York time (ET) and Western European time. Italy is the furthest east we can go. You might currently be titled Titles are all over the place in this space. If the work above matches what you already do, apply. We'll go on what you've shipped. You've evaluated retrieval systems: RAG, hybrid search, reranking. You've worked with agent orchestration frameworks like Temporal, LangGraph, or the OpenAI Agents SDK, and you know how long-running tool use goes wrong. You have a background in information retrieval or search relevance. You've worked somewhere an agent's output carried financial or compliance consequences. You've built internal tooling that non-engineers used on their own to label and review model output. This is a fully remote, full-time permanent position available to candidates located within the New York (ET) through Western Europe time zones, with flexible working hours to support collaboration across regions. #J-18808-Ljbffr

Trabajos chat en SantanderCrear alertas

Búsquedas de empleo más populares en Santander

Lugares de trabajo chat más populares