Company Overview
Grae AI is building AI-agent–driven platforms for the life sciences domain, focused on modernizing healthcare operations and clinical research workflows. Our work centers on designing and deploying production-grade AI systems that improve productivity, enable data-backed decision-making, and automate complex, high-impact processes across healthcare and research envi
ronments.We combine deep AI systems engineering with domain understanding to deliver platforms that operate reliably in real-world, regulated settings.
What You Will Work On
You will contribute to the design, development, and operation of AI-powered healthcare workflows, including:
- Intelligent conversational systems
- AI-assisted document understanding and data extraction
- Patient-facing dashboards and interfaces
- Secure, scalable backend services and APIs
All work is production-focused, designed for live healthcare environments, with a strong emphasis on reliability, correctness, and long-term maintainability.
Core Responsibilities
• Design and implement scalable AI systems using modern LLM and Agent-based architectures.
• Build and integrate backend services supporting AI-driven workflows and orchestration.
• Design agent-based and workflow-driven AI systems with observability and guardrails.
• Integrate AI systems with frontend applications and user interfaces.
• Design cloud-native architectures and manage production deployments.
• Build and maintain CI/CD pipelines for backend, frontend, and AI workflows.
• Own systems end-to-end from design to production support.
Required Skills & Experience
- Experience or exposure to production grade end-to-end AI system design, including LLMs, RAG pipelines, and agentic workflows
- Strong familiarity with AWS-based architectures, including services such as Lambda, API Gateway, Step Functions, S3, DynamoDB, Bedrock, Cognito, VPCs, IaC, CDK, Cloudformation
- Experience with multi-agent orchestration, tool calling, and workflow coordination (e.g., Strands Agents, LangChain, LangGraph, or similar frameworks)
- Experience building data ingestion, document processing, storage, and retrieval pipelines at scale
- Designing APIs and contracts for frontend consumption, with attention to latency, streaming, pagination, and error handling
- Integrating AI systems with web applications, including dashboards, chat interfaces, uploads, and real-time updates
- Designing and maintaining CI/CD pipelines across backend, frontend, and AI components
- Experience with deployment strategies, environment separation (dev / QA / prod), and release reliability
- Understanding of observability, scalability, fault tolerance, and operational readiness
- Ability to reason about trade-offs in regulated or high-impact domains
- Solid fundamentals in object-oriented programming using Python and TypeScript
Evaluation Criteria
Candidates are evaluated on:
- System design and architectural thinking
- Full-stack engineering depth
- Understanding of AI systems in production
- Cloud and infrastructure maturity
- Ownership mindset and ability to operate end-to-end
- Ability to adapt and learn in fast-paced start up environments
What This Role Is Not
- This is not a research-based role
- This role is not limited to frontend-only or backend-only work, everyone does everything
- This is not focused on experimental or POC systems
Why This Role Matters
You will work on systems intended for real-world healthcare usage at the forefront of AI in Healthcare, where reliability, correctness, and clarity are critical. This role offers significant technical depth, ownership, and impact, with the opportunity to shape AI systems that meaningfully improve healthcare and clinical workflows.