AI Solution Engineer

AI Solution Engineer
Hybrid - must be onsite in NYC every Tuesday
9-12 months

We are looking for an 8+ years of experience AI Solution Engineer to design, build, and deploy enterprise-grade AI applications from concept to production. This hands-on engineering role spans frontend, backend, AI, cloud, and data platforms. The successful candidate will be partnering with business stakeholders, end users, and product owners to turn requirements into secure, production-ready AI products.

The ideal candidate can gather requirements, design scalable architectures, develop modern React applications, build backend APIs, implement AI capabilities, engineer data platforms, and deploy secure cloud-native applications. They take ownership from concept through production deployment, monitoring, and continuous improvement.

Key Responsibilities

• Design, build, and deploy end-to-end AI-powered enterprise applications.
• Create scalable, secure, and maintainable solution architectures.
• Build solutions with LLMs, Retrieval-Augmented Generation (RAG), AI agents, prompt engineering.
• Develop and orchestrate multi-agent AI workflows using modern agent frameworks and tool calling.
• Must have Built modern frontends with React, TypeScript, Vite, and Tailwind CSS.
• Develop backend services and REST APIs with Python, FastAPI, and Flask.
• Integrate AI applications with enterprise systems, APIs, databases, authentication providers, and business applications.
• Design and implement Azure Data Lake, ETL/ELT pipelines, Spark/Databricks workflows, and Lakehouse architectures.
• Deploy and operate cloud-native applications with Azure, Docker, Kubernetes, and CI/CD pipelines.
• Implement secure authentication with Microsoft Entra ID, OAuth2, JWT, or SAML.
• Establish AI evaluation frameworks, including regression tests, benchmark datasets, human review loops, and acceptance criteria.
• Optimize AI applications for latency, scalability, reliability, and cost.
• Write unit, integration, and end-to-end tests.
• Partner with end users, product owners, and the Lead Product Engineer to gather requirements, run demos, and incorporate feedback.
• Ensure Responsible AI, governance, security, compliance, monitoring, and observability.

Product End-to-End Delivery

• Own the full AI product lifecycle, from ideation to production support.
• Define technical architecture, roadmaps, milestones, and release strategies.
• Translate business requirements into production-ready AI solutions.
• Build frontends, backends, AI services, APIs, and data pipelines.
• Manage production releases, monitoring, and continuous improvement.
• Create technical documentation and mentor engineers.

Required Technical Skills

• AI/ML: LLMs, prompt engineering, RAG, AI agents, MCP, function calling, semantic search, vector databases, LLM evaluation, and guardrails.
• Programming: Python, SQL, JavaScript, and TypeScript.
• Frontend: React, Vite, Tailwind CSS, HTML5, CSS3
• Backend: FastAPI, Flask, REST APIs, OpenAPI, Gemma preferred.
• Data Engineering: Azure Data Lake, Azure Data Factory, Databricks, Spark, Delta Lake, ETL/ELT, and lakehouse architecture.
• Cloud: Azure OpenAI, Azure AI Foundry, Azure AI Search, AKS, Azure Functions, Azure App Service, Cosmos DB, Azure SQL, Key Vault, and Azure API Management.
• DevOps: Git, GitHub, GitHub Actions, Azure DevOps, Docker, Kubernetes, Helm, and CI/CD.
• Security: Microsoft Entra ID, OAuth2, JWT, and secrets management.

Preferred Qualifications

• 8+ Proven experience delivering enterprise AI products from concept to production.
• Experience in healthcare or another regulated industry.
• Experience with HL7 v2, FHIR R4/R5, OMOP CDM, and Epic/Epic Clarity. (Optional)
• Experience with Model Context Protocol (MCP)
• Strong communication, stakeholder management, and Agile/Scrum delivery skills.