Principal AI Architect and Engineer

Job Description

Insight Global is seeking an exceptional AI Architect / Engineer with deep experience in LLMs, python backend systems, and production architecture, to help push the boundaries of what AI can do in highly complex, regulated environments.

This is not a surface-level prompt engineering role. You will work at the core of our AI architecture, designing, testing, hardening, and scaling LLM-powered systems that operate at massive scale and high complexity.

• Design, build, and maintain LLM-driven backend systems processing millions of tokens daily.
• Work hands‑on with leading models including GPT, Claude (API), Codex, and Gemini.
• Architect, optimize, and maintain RAG pipelines using semantic and hybrid search techniques.
• Develop and enforce quality controls, testing checkpoints, and evaluation layers to detect and prevent:
  • Hallucinations
  • Semantic drift and collapse
  • Model degradation at scale
• Implement guardrails and output validation frameworks to ensure safety, accuracy, and reliability.
• Use multiple LLMs to cross‑validate and audit outputs in production workflows.
• Build secure, production‑ready prompt frameworks, system prompts, and protocols.
• Collaborate on platform modernization and next‑generation SaaS architecture.
• Stay current on:
  • New LLM releases and model updates
  • Behavioral changes and regressions
  • Emerging AI platforms relevant to healthcare and insurance

• Python‑first backend (Python handles the vast majority of system logic).
• Heavy use of:
  • LLM APIs
  • Semantic search
  • Elasticsearch
  • RAG architectures
• Secure, high‑volume, real‑world production workloads.
• AI systems operating at the edge of current model limits.

• Engineers who eat, sleep, and breathe AI.
• People who enjoy solving problems no one has solved before.
• Candidates who can handle direct feedback and high standards.
• Those who want autonomy, ownership, and technical depth over buzzwords.

• Work on real‑world AI systems with immediate impact in healthcare.
• Solve problems that push modern LLMs to their limits.
• Collaborate with deeply technical leadership.
• Competitive compensation and flexibility.
• Opportunity to shape the future of AI‑driven medical policy intelligence.

We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment regardless of their race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances.

If you need assistance and/or a reasonable accommodation due to a disability during the application or recruiting process, please send a request to . To learn more about how we collect, keep, and process your private information, please review Insight Global's Workforce Privacy Policy:

• Expert‑level backend engineering experience with Python in production environments.
• Deep, hands‑on expertise with Large Language Models (LLMs), including model behavior, strengths, limitations, and cost/performance tradeoffs.
• Proven experience working with multiple model families, including GPT, Claude (API), and Gemini, in real‑world systems.
• Strong hands‑on experience with:
  • Retrieval‑Augmented Generation (RAG)
  • Semantic search (hybrid keyword + vector)
  • Prompt engineering at scale (chaining, instruction hierarchy, few‑shot design)
• Demonstrated ability to identify, diagnose, and mitigate LLM failure modes, including:
  • Hallucinations
  • Semantic drift and collapse
  • Model degradation over time or scale
• Experience designing and enforcing guardrails, validation layers, and quality controls for AI systems.
• Production experience building LLM‑driven backend systems that handle high‑volume workloads.
• Experience working in or with regulated domains, such as healthcare, medical policy, insurance, or…