Senior AI-Powered Full Stack Web Developer

This is a remote position.

The Senior AI-Powered Full Stack Web Developer will lead the design, development, and optimization of Thrivelab's telehealth platform, leveraging AI as a core component of both the development process and the product experience.

This role is responsible for building scalable full-stack applications, integrating AI and LLM-powered capabilities, maintaining cloud infrastructure on AWS, and driving technical excellence across frontend, backend, and DevOps functions.

The ideal candidate combines strong software engineering expertise with an AI-first mindset — using modern AI tools not as an occasional aid but as a primary development workflow to accelerate delivery, improve code quality, and create innovative patient-facing solutions for a fast-growing telehealth platform.

This role supports Heroship and works within the broader Thrivelab technology team, collaborating closely with product, design, clinical operations, and engineering stakeholders across the organization.

Education

Bachelor's degree in Computer Science, Software Engineering, or a related technical field preferred. Equivalent professional experience demonstrating the same depth of knowledge is equally considered.

Experience

Must have:

• 5+ years of professional web development experience with demonstrated progression in full-stack roles
  

• Demonstrated, habitual use of AI coding tools (Cursor, Claude Code, GitHub Copilot, or equivalent) as part of daily development workflows — this is a core requirement, not a bonus
  

• Strong frontend expertise with React — including performance optimisation, component architecture design, and state management
  

• Solid backend experience with Node.js, NestJS, or similar frameworks
  

• Experience with relational databases (PostgreSQL, MySQL) including schema design and complex query optimisation
  

• Hands-on experience with AWS services — Lambda, S3, CloudFront, ECS/Fargate
  

• Experience with CI/CD workflows and containerised environments using Docker and ECS
  

• Proven track record delivering production-grade applications and contributing meaningfully to architecture decisions
  

• Strong communication skills with both technical and non-technical stakeholders
  

Nice to have:

• Hands-on experience integrating LLM APIs (OpenAI, Anthropic Claude, Gemini) or building RAG workflows
  

• Experience with AI agent frameworks such as LangChain, LlamaIndex, or CrewAI
  

• Experience with Next.js — SSR, SSG, and API routes
  

• Familiarity with TanStack tools including React Query and TanStack Router
  

• Experience in healthcare, HIPAA-compliant systems, or telehealth platforms
  

• Experience with infrastructure-as-code tools such as Terraform or AWS CDK
  

• Familiarity with microservices or event-driven architectures
  

• Experience with vector databases (Pinecone, Weaviate, pgvector) for AI and semantic search use cases
  

Licenses

None required.

Technical Skills Summary

• React, TanStack Query, TanStack Router, Next.js (SSR/SSG), component architecture, accessibility
  

• NestJS, Node.js, REST APIs, GraphQL, PostgreSQL, MySQL
  

• Cursor, Claude Code, GitHub Copilot, OpenAI API, Anthropic API, RAG workflows, LangChain, LlamaIndex
  

• AWS (Lambda, ECS/Fargate, S3, CloudFront), Docker, CI/CD, Terraform, AWS CDK
  

• HIPAA compliance, security best practices, code quality, testing, technical documentation
  

Behavioural & People Capabilities

• AI-first mindset — you reach for AI tooling instinctively, not reluctantly, and hold yourself to high standards on output quality
  

• Strong engineering judgement — able to make and defend architecture decisions, identify technical debt, and balance velocity with quality
  

• Clear communicator — can explain complex technical tradeoffs to product managers, clinical stakeholders, and leadership without jargon
  

• Collaborative approach to engineering — actively shares knowledge, mentors on AI-augmented practices, and elevates the team
  

• Self-directed and accountable in a fully remote environment — manages delivery timelines and flags blockers proactively
  

• Adaptable — comfortable operating across frontend, backend, infrastructure, and AI integration within the same sprint