Senior AI Agent & Workflow Engineer
hace 18 horas
Barcelona
ph3Job Overview /h3 pSenior AI Engineer – Agentic Workflows to build the skills, tools, and agents that power our most advanced products incorporating generative AI—and to bring them together into reliable, production‑ready workflows. /p h3Role Description /h3 pYou will work closely with business and product teams to translate high‑level problems into structured agentic workflows and production‑ready solutions. /p pYou will design multi‑step agentic systems using LangGraph and integrate leading LLM providers. You will be asked to work smart and efficiently with Claude Code and similar tools as part of your day‑to‑day engineering workflow to accelerate delivery and improve code quality. /p pA key part of the role is establishing strong evaluation practices to measure quality, reliability, and cost, while maintaining a high sense of ownership from design through deployment. /p h3Responsibilities /h3 ul liDesign Agentic Workflows: Architect end-to-end workflows using LangGraph (or similar), breaking complex problems into composable steps, states, and policies /li liProblem Decomposition Solution Design: Translate high‑level business problems into structured agentic solutions, defining workflows, components, and trade‑offs across multiple design options. /li liBuild Skills, Tools, and Agents: Implement reusable skills, tools and agents, and compose them into workflows that are maintainable and testable. /li liChoose the Right Building Block: Demonstrate strong judgement on when to build a skill vs. a tool vs. an agent vs. a workflow, based on problem decomposition, system design trade‑offs, and long‑term maintainability—balancing accuracy, complexity, observability, and long‑term reuse. /li liModel Strategy Integration: Integrate and operate multiple LLM providers, optimising for latency, cost, and output quality /li liPerformance Optimization: Optimize prompt engineering, token usage, chunking strategies, and inference efficiency across the platform. /li liEvaluations Quality: Define and implement evaluation strategies (offline and online), datasets, metrics, and guardrails to validate agent behaviour and measure regression over time. /li liData Structuring Validation: Design typed schemas (e.g., Pydantic models) for reliable data flows, tool contracts, and structured outputs. /li liObservability Debugging: Implement logging, tracing, and monitoring for agentic systems using tools like Langfuse or LangSmith. /li liAI-Accelerated Engineering: Use AI assistants (including Claude Code) in day‑to‑day work for prototyping, refactoring, testing, and documentation—while applying strong engineering judgement /li liCross-functional Collaboration: Partner with data scientists, engineers, and product to translate requirements into robust agentic capabilities and deliver measurable value /li liWork alongside experts in various technological domains. /li liEnhance your skills with real‑world experience /li liContribute to a team that values your input and creativity /li /ul h3Must Have /h3 ul li5+ years Python development with strong software engineering fundamentals /li liHands‑on experience building production systems with Large Language Models /li liHigh ownership proactive communication: Delivers assigned outcomes autonomously, keeping progress visible and proactively surfacing blockers, changes in approach, and trade‑offs—seeking input early when needed /li liProven experience with LangGraph or similar agentic frameworks (LangChain, other orchestration frameworks acceptable) /li liStrong understanding of evaluation methodologies for LLM/agent quality (datasets, metrics, human review, regression testing) /li liAbility to reason about when to build a skill vs tool vs agent vs workflow, with clear trade‑offs /li liProven ability to decompose complex, ambiguous business problems into scalable technical solutions, from high‑level requirements to detailed design. /li /ul h3Nice to Have /h3 ul liComfort using AI assistants (e.g., Claude Code) as part of the daily engineering workflow /li liFamiliarity with LLM observability tools (Langfuse, LangSmith, etc.) /li liBackground with vector databases and RAG patterns /li liUnderstanding of cost optimisation and token accounting in LLM systems /li liProduction experience with async Python patterns (asyncio, concurrent request handling) /li liExperience with Azure deployment and cloud‑native architectures /li liKnowledge of evaluation frameworks and metrics for AI output quality /li /ul h3What You’ll Bring /h3 ul liProblem Decomposition Solution Design: Ability to take ambiguous, high‑level business problems and systematically break them down into actionable components, defining multiple solution approaches and selecting the most appropriate one based on trade‑offs (accuracy, cost, complexity, and scalability). /li liClearly defined workflows (agents, tools, skills, orchestration) /li liTechnical specifications and contracts for each component /li liEvaluation criteria, success metrics, and test strategy /li liImplementation‑ready designs executable end‑to‑end /li liArchitectural thinking: Ability to take ill‑defined, complex AI problems and decompose them into clean, modular components /li liProduction mindset: Comfortable shipping robust, observable, maintainable AI systems—not prototypes /li liLLM fluency: Deep practical knowledge of how to work effectively with large language models /li liSystems perspective: Understanding of how AI components integrate with APIs, databases, async workers, and monitoring /li liInitiative: Comfortable owning full‑stack design decisions and driving technical direction with the team /li /ul h3Benefits /h3 ul liCompetitive salary /li liYearly bonus /li liFlexible working model to support work‑life balance /li liOption to work abroad up to 25 days yearly /li liOver 300 euros to set up your home office and additional monthly home office allowance /li liWide range of internal and external trainings, including English, German and Spanish classes depending on the needs /li liTicket restaurant and Health Insurance with the flexibility to exchange it for other benefits /li liLife and accident insurance /liliCollective Life retirement Plan /li li2000 referral bonus if you bring other talented people like you to the company /li liSpecial banking and insurance conditions plus Exclusive Employees discounts /li liFunctional diversity benefits /li liStock options and mortgage benefits /li /ul h3Location /h3 pBarcelona, Poblenou. /p h3Schedule /h3 pFull Time. Hybrid remote working model. /p h3Recruiter /h3 pLaura Santamaría Rodríguez /p h3Equal Opportunity Employer Statement /h3 pAt Zurich, we are an equal opportunity employer. We attract and retain the best-qualified individuals available, regardless of race/ethnicity, religion, gender, sexual orientation, age, or disability. /p /p #J-18808-Ljbffr