pierpaolo28/Awesome-FDE-Roadmap

🚀 The definitive roadmap to becoming a Forward Deployment Engineer (FDE). Master AI Agents, Enterprise Data Architecture, and Strategic Consulting. Bridging the gap between HQ and the field. Inspired by the "Delta" role at Palantir, OpenAI, and Scale AI.

What it solves

Forward Deployment Engineering (FDE) solves the gap between "perfect" software built at a company's headquarters and the "messy reality" of a client's environment. Standard software often fails when it encounters real-world obstacles like corrupt data, air-gapped servers, or complex legacy infrastructure. FDEs act as technical special ops to bridge this gap, ensuring that high-stakes projects actually deliver value in the field.

How it works

The project provides a comprehensive roadmap for the FDE role, which blends software engineering, data architecture, and strategic consulting. It covers:

  • Technical Foundations: Mastering data engineering (SQL, Spark, dbt), cloud infrastructure (GCP, Kubernetes, Terraform), and security (VPC controls).
  • Applied AI: Using the Google Agent Development Kit (ADK) and Agents CLI to build, evaluate, and deploy multi-agent systems.
  • Consulting Strategy: Applying frameworks like the Pyramid Principle and MECE to manage stakeholders and translate business needs into technical requirements.
  • Evaluation: Implementing rigorous "inner loop" (development) and "outer loop" (production) testing to ensure AI reliability.

Who it’s for

This roadmap is for engineers who want to transition into a hybrid, high-impact role that involves both deep technical work and direct engagement with high-stakes stakeholders like CTOs and CEOs. It is ideal for those who enjoy solving complex, real-world problems in challenging or restricted technical environments.

Highlights

  • A structured curriculum covering data engineering, cloud architecture, and consulting.
  • A deep dive into the Google Agent Development Kit (ADK) for building multi-agent systems.
  • Guidance on the "Agents CLI" for managing the lifecycle of AI agents from prototype to production.
  • A framework for "LLM Systems Evaluation," including model-as-a-judge techniques to ensure production reliability.
  • Practical resources for enterprise RAG (Retrieval-Augmented Generation) and infrastructure-as-code.

Related

  • Project
    alookai/alook

    Alook is a collaboration platform that gives local AI coding agents a persistent identity and shared workspace, allowing teams to interact with them from any device while keeping the agents running securely on their own machines.

  • Project
    nixopus/nixopus

    An open-source deployment platform featuring an autonomous AI agent that handles app deployment, configuration generation, and self-healing fixes.

  • Project
    nateherkai/roast-room

    Roast Room is a Node.js web app that uses Claude Code sub‑agents to simulate a council of seven famous business figures. You feed a decision, the agents argue, score options, and produce a verdict PDF—all driven by curated “brains” built from each person’s public work.

  • Project
    Gsync/jobsync

    A self-hosted job search assistant that uses AI to automate job discovery, review resumes, and match candidates to job listings while keeping data private.