Full-stack Engineer (Generative AI Prototyping & MVP)
Who we are:
AI workflow is broken. Digital work is buried under copy-paste routines, fragmented tools, and repetitive tasks that drain our time and focus.We're building IrisGo — your AI butler for the AI PC era. It understands how you work, observes your context, and automates what you shouldn’t have to do. We’re a small team of engineers and builders driven to solve hard problems — from browser automation to computer use, from local LLMs to full workflow orchestration. We believe the future of productivity is ambient, intuitive, and immersive. Our goal: reclaim your time and focus, one automated task at a time.Based in California and Taipei, we bring deep roots in full-stack engineering, machine learning, and product design. If you want to build the future of human-computer interaction, we’re hiring.About the Role:
We’re looking for a Full-Stack Engineer with hands-on experience in Generative AI to lead the rapid development of prototypes and the first MVP for IrisGo.ai. In this role, you won’t just write code—you’ll bring product ideas to life using the latest AI tools and frameworks. You’ll work closely with visionary founders, product thinkers, and engineers to quickly turn abstract concepts into functioning applications that can be tested, validated, and scaled. This is a high-impact role for someone who moves fast, embraces ambiguity, and loves building from zero. If you thrive in fast-paced environments and enjoy creating full-stack AI-powered applications from scratch—this is the job for you.What You’ll Do:
- Rapidly design and develop full-stack applications as functional prototypes and early MVPs.
- Work across the stack to ship GenAI-powered user experiences with speed and clarity.
- Apply Generative AI tools (e.g., RAG, vectorDBs, agentic frameworks, prompt workflows) to real-world product use cases.
- Use AI-assisted development tools (e.g., Cursor, Copilot, Windsurf) to accelerate coding and prototyping.
- Deploy applications to the cloud (AWS, GCP, Supabase, etc.) and manage dev environments.
- Build and integrate external APIs, LLM platforms, and third-party services into prototypes.
- Incorporate user feedback and data to improve usability and functionality quickly.
- Maintain a high level of awareness around emerging GenAI technologies and product patterns.
- Balance building "scrappy" experimental code with laying a foundation for scale when the time is right.
What You Must Bring:
- 3+ years of full-stack development experience, including AI-powered products or prototypes.
- Demonstrated experience building applications that leverage LLMs and GenAI components.
- Strong knowledge of GenAI building blocks: Prompt engineering, Retrieval-Augmented Generation (RAG), Vector databases (e.g., Pinecone, Weaviate), Agent frameworks (e.g., LangGraph, CrewAI), and Evals, guardrails, and prompt chaining tools.
- Front-end experience with JavaScript/TypeScript, HTML, CSS, and modern frameworks like React or Vue.
- Backend expertise with Python and frameworks like FastAPI or Flask.
- Comfortable with SQL and NoSQL databases (e.g., PostgreSQL, MongoDB).
- Proficiency with Git and modern dev workflows.
- Strong understanding of cloud infrastructure and deployment tools.
- Hands-on experience using AI development tools such as Cursor, Copilot, or Windsurf.
- Excellent communication and collaboration skills across technical and non-technical teams.
- A bias toward action, rapid learning, and a pragmatic, product-focused engineering mindset.
Nice to Haves:
- Experience launching MVPs in startup or innovation-focused environments.
- Familiarity with rapid prototyping tools or no-code/low-code environments.
- Interest in early user testing and shaping product direction.
- Open-source contributions in GenAI or tooling.
- Experience with serverless architectures or edge deployment.
Originally posted on Himalayas
Apply To this Job