Senior GenAI Engineer (Remote)

Localización: España

We are looking for a Senior GenAI Engineer to design and build advanced generative AI workflows that power our next-generation coverage analysis platform. You will architect complex, multi-step agentic systems using modern orchestration frameworks, transforming ambiguous business challenges into scalable, production-grade AI solutions. Operating at the intersection of system design and AI innovation, you will drive the technical evolution of how our platform leverages large language models.

What You’ll Do

• Architect GenAI Workflows — Design end-to-end agentic systems using LangGraph, structuring complex problems into modular, composable steps and nodes.
• Build Orchestration Layers — Implement robust LLM orchestration with LiteLLM or similar tools, managing multi-model strategies, fallbacks, routing, and cost efficiency.
• Data Structuring & Validation — Create reliable, typed data flows using Pydantic models across pipelines, APIs, and internal services.
• Model Strategy & Integration — Evaluate and integrate multiple LLM providers (OpenAI, Claude, etc.), optimizing for latency, cost, and output quality.
• Observability & Debugging — Implement logging, tracing, and monitoring for AI systems using tools such as Langfuse or LangSmith.
• Performance Optimization — Improve prompt engineering, token usage, chunking strategies, and inference efficiency across the platform.
• Cross-functional Collaboration — Work closely with data scientists, AI engineers, and product teams to refine prompts, deploy systems, and shape new features.

Must-Have Experience

• 5+ years of Python development with strong software engineering fundamentals.
• 2+ years building production systems powered by Large Language Models.
• Hands-on experience with LangGraph or similar agentic/orchestration frameworks (LangChain, etc.).
• Deep expertise with Pydantic for structured data modeling and validation.
• Strong understanding of LLM capabilities, limitations, prompt engineering, and evaluation methodologies.
• Production experience with async Python (asyncio, concurrent request handling).
• Ability to design and implement complex system architectures with minimal guidance.

Nice to Have

• Experience with LiteLLM or multi-model abstraction layers.
• Familiarity with LLM observability tools (Langfuse, LangSmith).
• Background in vector databases and RAG patterns.
• Understanding of cost optimization and token accounting.
• Experience with Azure and cloud-native architectures.
• Knowledge of evaluation frameworks and metrics for AI output quality.

Technical Expectations

• Architectural thinking — Ability to decompose ambiguous AI problems into clean, modular components.
• Production mindset — Focus on building robust, observable, maintainable systems rather than prototypes.
• LLM fluency — Deep practical knowledge of working effectively with large language models.
• Systems perspective — Understanding of how AI components interact with APIs, databases, async workers, and monitoring layers.
• Initiative & Ownership — Comfortable driving technical direction and owning end-to-end design decisions.

What We Offer

• 💰 Highly competitive compensation, aligned with senior-level expertise and market benchmarks.
• 🌍 Work with a global enterprise leading innovation in AI-driven solutions — a truly international environment.
• 🚀 Career growth plan with continuous learning, technical leadership opportunities, and exposure to cutting-edge AI projects.
• 🏡 100% remote work, with flexibility, autonomy, and impact.