Lead AI Software Engineer / Architect

Lead AI Software Engineer / Architect

Full-Time | Direct Hire

US Citizen, Green Card, H4, TN Visa or E3 Visa

No Visa Transfer or Sponsorship Available

Must currently live in the United States

Our client is recognized as a leader in our field for innovation in service, attention to detail, our stellar team members, and making the complex easier. If this interests you, we’d love to have you join our rapidly growing team!

Position Summary:

We are looking to hire a talented, eager, and skilled Lead AI Software Engineer / Architect, AI & Automation to join our team in a remote position. The Senior Software Engineer, AI & Automation owns the design, delivery, and reliability of AI-powered features and automation systems across our platform, while continuing to contribute to product development within our core application stack. This role bridges software engineering and applied AI — building LLM-powered features, designing automated workflows, and making architecture and safety tradeoffs with minimal oversight.

The Lead AI Software Engineer / Architect AI & Automation works across Python, LLM APIs (OpenAI, Anthropic, or equivalent), LangChain/LangGraph, vector databases, PHP, Symfony, Node.js, TypeScript, React, Next.js, MongoDB, PostgreSQL, and Redis.

Responsibilities of this position include but are not limited to:

• Design, build, and maintain AI-powered features and automated workflows that integrate LLMs, agents, and automation tooling into our platform.
• Design and implement retrieval-augmented generation (RAG) systems, including embedding pipelines, vector search, and chunking strategies, to ground AI outputs in our data.
• Build and orchestrate multi-step AI agents and automated workflows that plan, use tools, and execute tasks with appropriate human-in-the-loop checkpoints.
• Contribute to development of new features and maintenance of existing functionality across our PHP/Symfony and Node.js/React application stack.
• Design and maintain evaluation (eval) harnesses and testing frameworks to measure AI system accuracy, reliability, and regression over time.
• Implement observability for AI systems, including tracing, logging, and cost monitoring, to catch failures and drift before they reach users.
• Establish and enforce guardrails, prompt-injection defenses, and human-in-the-loop review so AI systems fail safely.
• Ensure AI and automation systems handle sensitive data appropriately and in accordance with compliance standards (HIPAA, SOC 2, GxP, ISO 27001), including preventing PHI or PII from being exposed to third-party AI services without appropriate safeguards.
• Partner with Product and Engineering to scope AI and automation initiatives, flagging risk, feasibility, and sequencing issues before implementation begins.
• Evaluate and select LLM providers, models, and frameworks based on cost, latency, and accuracy tradeoffs for each use case.
• Identify and reduce technical debt across both AI/automation infrastructure and application layers.
• Optimize LLM and automation costs through model routing, caching, and efficient prompt and context design.
• Support developer velocity by maintaining stable AI/automation environments, tooling, and clear documentation.
• Mentor Software Engineers on AI engineering principles, prompt design, and automation best practices.
• Write clean, maintainable, and testable code aligned with team standards and architectural goals.
• Participate in peer code reviews to ensure quality, consistency, and knowledge sharing.
• On-Call Rotation: when scheduled, be available after hours for the duration of the assigned week to respond to critical issues and support operational continuity.
• Complete all required initial and ongoing training within a reasonable or provided timeframe.

The ideal candidate will have the following experience, skills, and knowledge:

• Bachelor’s degree in Computer Science/Information Technology, or equivalent experience.
• 5+ years of professional experience in software engineering, including 2+ years building and shipping production LLM-powered or automation systems.
• Hands-on experience with LLM APIs (OpenAI, Anthropic, or equivalent) and prompt/context engineering for production use cases.
• Experience building retrieval-augmented generation (RAG) systems, including vector databases (e.g., Pinecone, pgvector, Weaviate) and embedding pipelines.
• Experience with agent orchestration frameworks (e.g., LangChain, LangGraph, CrewAI) and tool-calling/function-calling design.
• Experience designing and maintaining eval harnesses and observability for non-deterministic AI systems.
• Experience with workflow automation tooling (e.g., n8n, Temporal, Zapier, or custom orchestration) for business process automation.
• Proficiency in Python, and professional experience with PHP/Symfony and modern JavaScript/TypeScript frameworks (React, Node.js) or similar.
• Experience with Docker and cloud infrastructure (AWS preferred) for model deployment and serving.
• Demonstrated experience owning an AI or automation system end-to-end, from design through production.
• Experience with, or working knowledge of, regulatory and security compliance standards (HIPAA, SOC 2, GxP, GDPR, ISO 27001), particularly as they apply to AI systems handling sensitive data.
• Knowledge of AI/ML systems, LLM capabilities and limitations, and emerging tools, with sound judgment about when to adopt them.
• Commitment to continual learning and staying current in a fast-moving AI landscape.
• Ability to learn new models, frameworks, and tools quickly and evaluate tradeoffs before adopting them.
• Excellent problem-solving and debugging skills, including debugging non-deterministic and probabilistic systems.
• Ability to communicate complex AI and automation tradeoffs, limitations, and risk to both engineers and non-technical stakeholders.
• Strong written and verbal communication skills.
• Demonstrated mentorship skills – provides guidance and technical direction to other engineers on AI engineering and automation practices.
• Attention to detail, with the ability to probe deeper into ambiguous or underspecified problems, including where AI outputs are unreliable or ungrounded.
• Ability to work independently and as part of a team.