Contract Senior AI Engineer: Production-Grade Agent Systems

NLP PEOPLE; Barcelona; Presencial; EUR 90.000 - 130.000; Jornada completa

Descripción de la vacante

LinkedIn is seeking a senior software engineer to design, develop, and deploy production-grade AI applications with an agent-first approach. You will build scalable RAG pipelines and integrate AI solutions with enterprise platforms using MCP and modern tooling.

You will define evaluation strategies, benchmarks, and quality frameworks to ensure reliable AI systems from prototype to production, and recommend architectures balancing LLM/SLM capabilities, cost, latency, and performance in complex

Formación

• 7+ years of experience building and shipping LLM-based applications into production environments.
• Proven track record with AI agents, orchestration frameworks, and enterprise AI solutions.
• Experience designing evaluation pipelines, automated benchmarks, LLM-as-a-Judge methodologies, and HITL processes.
• Deep knowledge of LLM/SLM capabilities, prompt and context engineering, and agentic system design.

Responsabilidades

• Design, develop, and deploy production-grade AI applications with an agent-first approach.
• Build scalable RAG pipelines and integrate AI solutions with enterprise platforms using MCP and modern tooling.
• Define evaluation strategies, benchmarks, and quality frameworks to ensure reliable AI systems from prototype to production.
• Recommend and implement the most suitable architecture, balancing LLMs, SLMs, hybrid approaches, cost, latency, and performance.

Conocimientos

Software engineering

AI agents

Evaluation pipelines

Prompt engineering

Human-in-the-Loop

LLM/SLM knowledge

Descripción del empleo

LinkedIn is seeking a senior software engineer to design, develop, and deploy production-grade AI applications with an agent-first approach. You will build scalable RAG pipelines and integrate AI solutions with enterprise platforms using MCP and modern tooling.

You will define evaluation strategies, benchmarks, and quality frameworks to ensure reliable AI systems from prototype to production, and recommend architectures balancing LLM/SLM capabilities, cost, latency, and performance in complex