Jobbeschreibung
Join a cutting-edge team in Germany to build and scale LLM-powered products that delight customers. We're seeking a battle-tested engineer who's shipped real AI features—not just prototypes. Work remotely with our innovative partner, collaborating closely with the Dev Lead on a live, production product. Take ownership across the stack and drive meaningful impact.
What You'll Do
- Build, integrate, and optimize LLM-powered features using APIs like OpenAI and Anthropic
- Design, iterate, and refine prompts, workflows, and systems for production use cases (e.g., RAG, conversational AI)
- Develop robust backend services with FastAPI, PostgreSQL, and analytics tools like Snowflake or AWS Redshift
- Deploy, monitor, and maintain cloud-based systems with a focus on reliability, observability, and scalability
- Contribute to the full stack as needed, including frontend with React, TypeScript, Vite, Tailwind CSS, and Supabase (Flutter a plus)
- Collaborate with the Dev Lead to support, extend, and evolve an established product
What We're Looking For
- Proven production experience shipping LLM features: API integrations, prompt engineering, and iterative improvements
- Hands-on expertise building AI applications like RAG systems, chat interfaces, or AI workflows
- Strong backend skills with FastAPI, PostgreSQL, and data platforms (Snowflake, AWS Redshift)
- Proficiency or solid willingness to work with frontend: React, TypeScript, Vite, Tailwind CSS, Supabase
- Experience with automation tools like n8n
- 3–5+ years of practical experience (professional, freelance, or open-source welcome)
Nice-to-Haves
- Docker / docker-compose, Git, AWS
- Audio/speech processing or call analytics (core to our product)
Setup & Perks
- Fully remote with a Germany-based partner
- European timezone preferred (or flexible alignment)
- Jump into an active product from day one and grow it with us