Senior AI Agent Engineer - Precision, Tooling & Evaluation

FirstIgnite; O Chazo; Presencial; EUR 90.000 - 130.000; Jornada completa

Descripción de la vacante

FirstIgnite is seeking a Senior AI Agent Engineer to design and ship long-running, multi-step agents that call various AI SDKs and external APIs. You will build evaluation suites, ensure accurate data extraction from long documents, and provide robust citations and confidence signals for review by humans.

The role focuses on precision, traceability, and reliable handoffs to humans, working with product and the full-stack team.

Formación

• 3+ years of engineering experience with LLM or agent systems
• Evaluated agents, not only models, for multi-step runs
• Integrated against external APIs and built reliable agent calls
• Comfortable with document pipelines: extraction, normalization, matching against sources
• Familiar with at least one LLM evaluation framework

Responsabilidades

• Design and ship long-running, multi-step, tool-using agents across AI SDKs
• Wrap APIs as tools for agents, including translating older systems
• Extract structured data from long documents and match to existing records
• Stand up eval suites and measure tool-use correctness and trajectory quality
• Create drafts with citations and confidence signals for fast human review
• Collaborate with product and domain experts to turn vague goals into measurable targets
• Instrument production traffic and generate synthetic datasets for testing
• Compare models and prompts across OpenAI, Anthropic, and open-weight options
• Bootstrap quality signals for features with no production traffic
• Write templates, docs, and tooling to run evals independently

Conocimientos

LLM systems

Agent tooling

API integration

Document processing

Evaluation frameworks

Herramientas

OpenAI Agents SDK

Anthropic Agent SDK

Vercel AI SDK

LangGraph

Temporal Cloud

Descripción del empleo

FirstIgnite is seeking a Senior AI Agent Engineer to design and ship long-running, multi-step agents that call various AI SDKs and external APIs. You will build evaluation suites, ensure accurate data extraction from long documents, and provide robust citations and confidence signals for review by humans.

The role focuses on precision, traceability, and reliable handoffs to humans, working with product and the full-stack team.