AI Engineer

What you’ll do

• Build and improve LLM-powered analytics features including agentic workflows, natural-language querying, retrieval-augmented generation (RAG), and tool-use across both structured and unstructured data.
• Contribute to text-to-SQL and semantic-layer systems that help non-technical users query complex healthcare datasets accurately and safely.
• Develop retrieval pipelines over document stores using vector search and hybrid keyword + semantic retrieval.
• Implement evaluation, guardrails, and hallucination checks, with accuracy on domain data as a non-negotiable requirement in healthcare.
• Help enforce data-governance and compliance controls in the AI layer, including derived-insights-only usage and no PHI/PII exposure, along with appropriate access controls.
• Integrate multiple tools and data sources into agent workflows, including a warehouse, campaign platforms, web, and document repositories.
• Deploy and maintain services on AWS, monitoring model performance, latency, and cost.
• Collaborate with product, analytics, and senior engineers to translate requirements into shipped features.

What you bring

• 2–4 years building production software, including hands-on experience with LLM/GenAI applications such as RAG, agents, or text-to-SQL through work, internships, or substantial personal projects.
• Solid Python and SQL; comfort querying a cloud data warehouse (Snowflake is a plus).
• Working knowledge of AWS and deploying services in the cloud.
• Substantive experience with LangGraph, CrewAI, n8n, or other agentic frameworks.
• Experience with AI-assisted coding and CI/CD processes.
• Familiarity with Node, React, or other JavaScript frameworks.
• Exposure to retrieval systems, embeddings, or vector search.
• Experiments-driven design using evaluation harnesses for change management.
• Understanding of prompt engineering and LLM guardrails to make outputs reliable, not just functional.
• Awareness of data privacy and compliance basics and willingness to build to them.
• Ability to own a feature or component end-to-end and collaborate across a team.

Nice to have

• Experience with healthcare/life-sciences data (claims, referrals, HCP, ICD-10) or another regulated data domain.
• Familiarity with HIPAA / PHI-PII constraints or de-identified / derived-insights data models.
• Exposure to agent orchestration frameworks and multi-tool workflows.
• Basic MLOps/LLMOps such as monitoring and cost/latency optimization.
• Background in analytics, BI, or data engineering.

Core technology and domain context

• Cloud: AWS (Lambda, S3, ECS/Fargate, API Gateway)
• Data warehouse: Snowflake, including SQL and semantic layers
• AI/ML: LLMs (OpenAI/Anthropic-class models, including Amazon Bedrock), RAG, embeddings/vector search, prompt engineering, function-calling / tool-use
• Data domains: healthcare claims, physician referrals, ICD-10 diagnosis, HCP engagement, campaign/media performance, survey/primary research
• Data and documents: vector databases, hybrid search, integrations such as Egnyte and Google Drive
• Governance: compliance-aware data access, PHI/PII handling, and source citation

Reports to: VP, Data Products & Technology · Department: Data Solutions & Analytics