Forward Deployed Engineer - DEV

Job Description

Job Description

Overview

FDEs at CVP are the rare engineers who get to do all of it — build, integrate, and open doors — and see the full arc of impact from a single deployment. You design the solution, wire the integrations, ship production code, and then watch a real agency change how it operates because of what you built. When that works, it creates the next opportunity: your technical reputation  is the growth motion. Engineers who thrive here want to own outcomes, not hand them off. 

You may be in an agency briefing one hour and debugging a container the next, shifting contexts without losing signal. You treat ambiguity as raw material — undefined problems aren't blockers, they're where the work starts. You surface requirements by asking the right questions, not by waiting for a spec. And when it's time to communicate, you write with the kind of precision that makes technical updates actually land with non-technical stakeholders. 

Fifer is our flagship enterprise GenAI platform: deployed entirely within agency cloud environments, zero data leaving premises, swappable LLMs, and multi-agent RAG. When agencies want to build AI-powered workflows, audit processes, expert assistants, or developer tooling, you are how that happens. You’ll extend Fifer through custom skills, MCP server integrations, and agent workflows built specifically for each customer’s mission. 

This role requires the ability to obtain a federal security clearance (US Citizenship Required).

Responsibilities

Build 

• Own technical delivery from discovery through production across multiple concurrent agency deployments 

• Write and ship production-grade integrations using Fifer’s APIs, modern web frameworks, and backend services 

• Build custom skills, agent configurations, and MCP server integrations that extend Fifer to customer-specific missions 

• Deploy and configure FiferAUDIT in customer cloud environments (AWS, Azure, GCP) ensuring FedRAMP compliance boundaries are met 

Embed  

• Work alongside agency technical teams and end users to understand workflows from the source, not requirements docs 

• Run discovery sessions, technical workshops, and working sessions that translate mission need into engineered solutions 

• Guide and train customers on prompt engineering, agent design, and agentic workflow optimization to maximize mission impact 

Influence  

• Partner directly with prospective and current agency clients as a technical advisor, conducting discovery sessions to uncover operational pain points, then rapidly prototyping and deploying tailored AI solutions that demonstrate immediate, tangible value 

• Build and maintain deep relationships with customer technical leadership and program stakeholders 

• Travel up to 50% to customer sites (primarily DC area) for on-site implementation, workshops, and relationship building 

Qualifications

• 5+ years of software engineering experience shipping production systems  
• Full-stack proficiency: JavaScript/TypeScript and/or Python; you can own a feature end to end 

• Cloud deployment experience (AWS, Azure, or GCP); comfortable with Kubernetes, Docker, Terraform, and CI/CD pipelines 

• Hands-on experience building or integrating LLM/GenAI-powered systems. You understand how model behavior, context windows, and retrieval quality affect what users experience 

• Expertise with AI agent harnesses (OpenCode, Pi, Claude Code, Cursor, Codex or similar) and practical experience building agent configurations and skills 

• Strong Linux system administration — you can install, configure, and debug on VMs and Kubernetes clusters without a runbook 

Preferred 

• Prior FDE, deployment engineering, or solutions engineering experience at a commercial product company 

• Experience working with federal civilian agencies (HHS, CMS, DHS, VA, DOL, or similar) 

• Experience with FedRAMP-compliant deployments