Senior Software Engineer, AI

Arya Health•New York, NY

About The Position

Our mission is simple but ambitious: to use AI to fix the broken economics and lost humanity of care. If you want to move fast and help build the future of healthcare with heart, you belong at Arya. About the Role We’re looking for a Senior Software Engineer in AI to join our team and embed intelligence into Arya’s workforce platform. You won’t be building foundation models—but you’ll be working with LLMs and AI toolkits to orchestrate workflows, automate decision-making, and improve how customers interact with Arya. Our team partners with Google’s Vertex AI group to shape their Agent development kit, and we’re looking for an engineer who can turn these cutting-edge tools into production-ready solutions for scheduling, shift eligibility, workforce management, and more. As a senior member of the engineering team, you’ll work closely with our Principal Architect and own AI-driven projects end-to-end: designing, prototyping, and deploying systems that make work smarter, more automated, and more intuitive for our customers.

Requirements

5+ years of software engineering experience, with 2+ years working with LLMs or AI frameworks.
Strong programming skills in Python or Node.js; familiarity with Pydantic and MCP architecture.
Expert in SQL and proficient with Postgres optimization.
Hands-on experience with Vertex AI, OpenAI, or other model APIs.
Familiarity with CI/CD pipelines and cloud environments (GCP preferred).
Experience designing APIs and backend services that integrate AI features at scale.
Clear communication skills and a collaborative, pragmatic mindset.

Nice To Haves

Experience with retrieval-augmented generation (RAG) pipelines and vector databases.
Exposure to compliance-aware AI systems in regulated industries.
Contributions to open-source AI/LLM frameworks.
Knowledge of monitoring/evaluation techniques for AI systems.

Responsibilities

Design and implement AI-powered workflows using Vertex AI Agents, Pydantic, Bland.ai and other orchestration frameworks.
Integrate LLMs into customer workflows (e.g., natural language scheduling, eligibility insights, onboarding automation).
Build scalable APIs and services that serve AI features reliably in production.
Implement evaluation, monitoring, and safety checks to ensure AI systems are accurate, fair, and trustworthy.
Collaborate with Product and Engineering to identify practical, high-impact AI use cases.
Document integration patterns and best practices for AI deployment.
Provide technical leadership and mentorship on AI integrations.