AI Platform / Software Engineer (Agentic Workflow)
Summary
We are seeking a hands-on AI Solutions Engineer to build the technical foundation that enables non-technical users and internal teams to create functional, production-ready systems with AI. In this role, you will not just build applications; you will create the scaffolding, guardrails, reusable components, and delivery standards that allow AI-assisted development to scale across the organization. For complex or higher-risk solutions, you will step in directly to design, harden, and productionize the implementation.
Responsibilities
Design Agentic Workflows: Build workflows that translate natural-language business requirements into structured specifications, application logic, integrations, testing, and deployable solutions
Build Reusable Capabilities: Create reusable skills, prompts, templates, connectors, APIs, and technical components that allow non-technical users to build solutions with coding agents.
Establish Guardrails & Governance: Implement automated testing, validation, security controls, permissions, audit logging, and risk-based human review for AI-generated systems
Solution Architecture: Define practical architecture patterns for APIs, data flows, integrations, authentication, agent tool usage, and deployment.
Integrate & Deploy: Connect AI-assisted solutions with enterprise systems, databases, authentication, cloud services, and production environments.
Production Hardening: Step in on complex or higher-risk solutions to review, refactor, troubleshoot, and harden AI-generated applications before production.
Required Technical Skills
AI & Agentic Engineering: Practical experience with coding agents such as Codex, Claude Code, Cursor, or similar tools, plus agent frameworks or SDKs such as LangGraph, OpenAI Agents SDK, CrewAI, or equivalent.
Software Engineering: Strong proficiency in JavaScript/TypeScript, Python, APIs, databases, and system integration.
System Architecture: Strong understanding of cloud platforms (AWS, Azure, or GCP), authentication, security, application architecture, and CI/CD.
Production Engineering: Experience with automated testing, observability, secrets management, permissions, reliability, and production troubleshooting.
LLM Engineering: Strong understanding of prompting, tool calling, structured outputs, RAG, evaluation, context management, and human-in-the-loop workflows.
Soft Skills & Qualities
Systemic Thinking: Focus on building the factory that makes software, rather than repeatedly building individual software pieces.
Technical Judgment: Balance delivery speed with security, reliability, maintainability, and cost.
Empathy for End Users: Understand both technical and non-technical user needs and turn complex engineering capabilities into simple, usable workflows.
Rapid Prototyping: A bias for action, experimentation, and iterative delivery.