Part-Time AI Software Developer / Co-Pilot (Healthcare SaaS)
Uses vibe coding tools (Specode, Convex) and LLMs; role is a technical co‑pilot leveraging AI-assisted code generation to rapidly build features.
About the Role
Part-time AI Software Developer / Technical Co‑Pilot to help transition a validated healthcare MVP into a secure, HIPAA-aligned production SaaS by leveraging AI generation tools and acting as the human expert for advanced API integrations, system logic, and performance optimization.
Job Description
Role
We are seeking a part-time AI Software Developer / Technical Co‑Pilot to help transition a validated healthcare MVP into a secure, production-ready SaaS application. You will work within a vibe-coding workflow (Specode front end, Convex backend) and leverage advanced LLMs to accelerate development while focusing on API integrations, backend logic, performance, and compliance.
Key Responsibilities
- Integrate and orchestrate multi-model LLM API calls within the existing backend infrastructure.
- Implement token and cost optimization strategies (context window management, prompt caching, token-saving techniques).
- Design hallucination control and verification layers: structured JSON outputs, system prompting, and guardrails to ensure clinical accuracy and data reliability.
- Develop and optimize Convex schemas, mutations, and queries to securely handle data flows.
- Collaborate with founder and compliance teams to maintain a secure, HIPAA-compliant architecture.
Requirements
- Current UNLV undergraduate (Junior/Senior) or Graduate student in Computer Science, Computer Engineering, or Data Science.
- Strong proficiency in TypeScript/JavaScript and Python.
- Familiarity with modern backend concepts, real-time databases (e.g., Convex, Firebase), and REST/GraphQL APIs.
- Hands-on experience with LLM APIs (OpenAI, Anthropic, Google Gemini or similar) and understanding of token mechanics and prompt engineering.
- Self-starter comfortable with ambiguity and independent research.
Compensation & Time Commitment
- Pay: $25.00 per hour.
- Expected hours: 10–15 hours per week.
Location & Schedule
- Hybrid remote in Las Vegas, NV. Extreme schedule flexibility to accommodate academic commitments.
Tools & Workflow
- Front end architecture: Specode.
- Backend/database: Convex (schemas, mutations, queries).
- LLMs: Claude 4.6 variants and other advanced models; experience with OpenAI/Anthropic/Google Gemini APIs is valued.
Notes
- This role emphasizes working as a technical co‑pilot—using AI generation tools for rapid development while contributing human expertise on complex integrations, system design, and compliance.