Forward Deployment Engineer

Location: Barcelona (Hybrid / Flexible)

Contract Type: Contractor Full-Time / Enterprise Project Engagement

Where elite tech talent meets world-class opportunities! At Xenon7, we work with leading enterprise clients and innovative startups on high-impact projects across Data, AI, Cloud, and Software Engineering. Our expertise in AI solution architecture and specialized technical talent allows us to partner with enterprise leaders on transformative initiatives, driving innovation and business growth.

We are seeking a high-caliber Forward Deployment Engineer (FDE) to sit at the intersection of enterprise AI platforms and executive Finance business functions for our Fortune 100 enterprise client. This role bridges advanced AI platform engineering with direct business impact—translating ambiguous financial challenges into working AI applications, deploying them into regulated client environments, and iterating in tight loops to drive measurable ROI.

Rather than building static models or waiting for formal spec sheets, you will operate as a product-minded technical lead. You will prototype user-facing tools in days, deploy agentic and RAG workflows on top of enterprise data stacks (Snowflake Cortex, Databricks Genie), and ensure high adoption across FP&A, Controllership, Treasury, and CFO leadership.

• Own the full lifecycle of AI solutions for Finance business units—from initial discovery with CFO stakeholders to production deployment, user adoption, and ROI measurement.
• Rapidly prototype vertical applications using Streamlit, Databricks Apps, FastAPI/Flask, or lightweight React interfaces within 1–2 weeks to gather real user feedback.
• Handle "last mile" execution: edge cases, data quirks, business rule exceptions, and user training to turn prototypes into sticky enterprise products.

• Build production-grade vertical AI tools leveraging Snowflake Cortex (Analyst/Search/Agents) or Databricks Genie (Genie Spaces, semantic models).
• Construct robust RAG pipelines incorporating advanced chunking, vector databases (Pinecone, Chroma, FAISS, Azure AI Search, Cortex Search), retrieval evaluation, grounding, and citation.
• Implement LLM orchestration frameworks (Lang Chain, Lang Graph, Llama Index) and apply rigorous prompt engineering with hallucination and accuracy evaluation discipline.

• Deploy applications inside heavily regulated enterprise environments, adhering strictly to RBAC, data residency, audit, and compliance constraints (SOX, GxP).
• Connect solutions to governed datasets, semantic models, and core enterprise platforms (SAP, Workday, Coupa, ERP) via secure REST APIs.
• Instrument all deployed apps with usage metrics, telemetry, and business outcome tracking from day one.

• Work directly with senior Finance leadership (CFO office, FP&A, Controllership) to translate ambiguous operational friction into crisp technical roadmaps.
• Extract reusable code components, prompt templates, evaluation harnesses, and retrieval patterns into shared enterprise assets for broader deployment.

• Experience: 5+ years of hands-on software development and full-stack AI application deployment.
• Product-Shaped Builder: Strong bias for action; comfortable shipping rough prototypes in Week 1 over polished spec documents in Week 4.
• Ambiguity Tolerance: Proven ability to navigate vague business problems without predefined specifications.
• Stakeholder Communication: Outstanding ability to interface directly with senior business leaders without requiring intermediary Business Analysts.

• Langu…