Principal AI Engineer

Insight Enterprises, Inc.

5d•Onsite

About The Position

We are seeking a Principal AI Engineer with deep experience in agentic systems, Google Cloud Platform and Vertex AI, large language models, clinical operations, and forward deployed engineering. In this client-facing consulting role, you will design and build AI-enabled applications that connect clinical and enterprise data, tools, workflows, and users through scalable, governed engineering patterns. You will bridge the gap between AI strategy and production implementation, partnering with clinicians, architects, data teams, security leaders, and operations stakeholders to deliver solutions that are useful, observable, secure, and ready for enterprise adoption.

Requirements

6+ years of experience in software engineering, cloud engineering, AI engineering, enterprise application development, or solution architecture, ideally in consulting, healthcare, or client-facing delivery environments.
Hands-on experience designing and building agentic AI applications, including orchestration, tools, memory, planning, multi-step workflows, RAG, and human-in-the-loop controls.
Strong experience with Vertex AI and the broader Google Cloud AI ecosystem, including Gemini models, Vertex AI Agent Builder, Vertex AI Search, Document AI, BigQuery, or related Google Cloud services.
Strong proficiency in modern programming languages and frameworks commonly used for AI application development, such as Python, TypeScript, Go, FastAPI, LangChain/LangGraph, or similar technologies.
Experience with GitHub Actions, Cloud Build, CI/CD, infrastructure-as-code (Terraform), containers (GKE and Cloud Run), APIs, monitoring, logging, environment promotion, and production release management.
Experience integrating AI with clinical and operational systems—EHRs, clinical documentation, and healthcare data standards such as HL7 and FHIR—including handling of PHI in regulated environments.
Understanding of AI evaluation, prompt/version management, automated testing, telemetry, tracing, monitoring, model behavior analysis, and operational support patterns.
Strong communication skills with the ability to translate technical tradeoffs into practical recommendations for executives, clinical leaders, platform teams, security stakeholders, and operations users.

Nice To Haves

Google Cloud Professional Machine Learning Engineer, Professional Cloud Architect, Generative AI Leader, or relevant Google Cloud and AI certifications.
GitHub, Google Cloud Professional DevOps Engineer, Kubernetes (CKA), Terraform, or cloud-native engineering certifications.
HIPAA, Responsible AI, or healthcare data and AI governance-related certifications are a plus.

Responsibilities

Design and build agentic AI systems that reason across tasks, use tools, retrieve context, and orchestrate multi-step workflows to automate and optimize clinical and operational processes, with human-in-the-loop review.
Develop AI solutions using Google Cloud technologies such as Vertex AI, Gemini models, Vertex AI Agent Builder, Vertex AI Search, Document AI, BigQuery, and related Google Cloud services.
Build LLM-powered pipelines to extract, summarize, and structure clinical notes and unstructured healthcare documents, improving accuracy, speed, and downstream operational workflows.
Establish CI/CD and MLOps pipelines, infrastructure-as-code, environment management, automated testing, release controls, and observability practices for AI-enabled applications on Google Cloud.
Build retrieval-augmented generation solutions that connect securely to clinical content, structured data, EHR and document repositories, and operational systems.
Implement authentication, authorization, RBAC, data access controls, logging, auditability, and guardrails to ensure AI systems handle PHI safely and operate compliantly in regulated healthcare environments.
Define and implement testing and evaluation approaches for agent performance, prompt quality, retrieval relevance, hallucination risk, response quality, latency, and reliability.
Serve as a hands-on, forward deployed senior engineer and technical advisor, embedding with client teams to make architecture decisions, resolve implementation blockers, and move AI solutions from prototype to production.
Mentor engineers and consultants while contributing reusable agentic design patterns, reference architectures, DevOps templates, and Google Cloud AI delivery accelerators for Insight.