Principal Engineer Software Development Engineering

Job Description

We are hiring a Principal Engineer to serve as an architect for Nexus, Enterprise AI platform for engineering workflows. This role partners with the existing platform architect to set technical direction across Nexus's hybrid on-prem and cloud architecture, lead design for agentic systems, MCP ecosystem, LLM gateway, memory and knowledge layers, and ensure the platform scales securely and reliably as adoption grows across FPG.

Essential Duties & Responsibilities:

• Architecture Leadership: Co-own end-to-end architecture for the Nexus platform across hybrid on-prem and cloud environments. Drive design decisions for agentic orchestration, MCP ecosystem, LLM gateway, memory and knowledge systems, observability, and platform applications.
• Technical Strategy: Define multi-quarter technical direction in partnership with engineering leadership. Translate platform vision into actionable architecture roadmaps that balance velocity, scalability, security, and operational maturity.
• Agentic Systems Design: Architect production-grade agentic workflows using LangGraph, Deep Agents, and modern agent frameworks. Establish patterns for tool use, multi-agent coordination, evaluation, and safety.
• Platform Standards: Establish and evolve standards for service design, API contracts, security, identity, observability, and developer experience across Nexus components and purpose-built applications.
• Cross-Functional Influence: Partner with InfoSec, Cloud Infrastructure, IAM, Networking, and product engineering teams. Lead architecture reviews, represent the platform in enterprise architecture forums, and shepherd designs through governance processes (ISAR, STARC, CAB).
• Technical Mentorship: Coach Staff and Senior engineers on system design, distributed systems, AI engineering, and production excellence. Raise the technical bar across the team through design reviews, code reviews, and architecture deep dives.
• Risk and Reliability: Identify architectural risks early, drive remediation, and lead the platform's evolution toward stronger environment separation, observability, and incident response maturity.
• Innovation: Track advances in LLMs, agentic frameworks, and AI infrastructure. Evaluate emerging technologies and lead targeted POCs that translate into platform capabilities.