The RoleYou're an experienced engineer who ships production AI features with confidence. You understand how to integrate LLM APIs and AI services into robust applications, architect scalable AI-powered systems, and deliver high-impact features that clients depend on.
What You'll Do- Design and implement end-to-end AI integrations: from LLM API selection to production deployment
- Architect AI-powered features that work reliably at scale
- Work independently on complex projects with minimal oversight
- Leverage LLM frameworks, vector databases, and prompt engineering to solve real problems
- Integrate cloud AI services and build custom AI tooling when needed
- Ship production-grade code that balances quality and velocity
- Collaborate with designers, product managers, and other engineers
- Contribute to technical decisions and architectural discussions
- Mentor junior engineers when needed
What We're Looking For- Production Expertise: Proven ability to ship production AI features end-to-end
- LLM Mastery: Deep hands-on experience with LLM APIs (OpenAI, Anthropic, etc.) and frameworks like LangChain
- Full-Stack Skills: Strong development across frontend (React/modern frameworks), backend (Python, Node.js, .NET), and infrastructure
- System Design: Can architect AI integrations that scale, handle errors gracefully, and provide good user experiences
- AI Tooling: Comfortable with vector databases, prompt engineering, embedding models, and emerging AI tools
- Quality Focus: You care about code quality, testing, and building systems that users can rely on
- Initiative: You identify problems, propose solutions, and drive projects to completion
Required Experience- 2-5 years of professional software engineering experience
- Demonstrated production AI experience (LLM integrations, AI-powered features)
- Advanced full-stack development skills
- Experience with modern cloud platforms (AWS, GCP, or Azure)
- Strong backend and infrastructure development skills applied to real production systems
- Proven ability to ship complex features independently
Nice to Have- Experience with RAG (Retrieval-Augmented Generation) systems
- Familiarity with vector databases (Pinecone, Weaviate, Chroma, etc.)
- Experience contributing to frontend features using modern frameworks when needed
- Background with API design and system integration
- Understanding of prompt engineering best practices
- Experience with deployment and DevOps practices
- Exposure to agentic AI systems
What Success Looks LikeIn your role, you'll:
- Ship production AI features with minimal guidance
- Own the technical direction of AI integrations on your projects
- Become the go-to expert on AI architecture and tooling
- Help raise the bar for how the team approaches AI engineering
- Build a track record of high-impact, reliable AI systems
- Grow as a leader by mentoring other engineers
