Software Engineer (Django, Next.js & LLM Applications)

Experience: 1-2 years Location: Hybrid Employment Type: Full-time About the Role We're looking for a full stack engineer who's comfortable working across the backend and frontend, and who's genuinely curious about building products powered by large language models. You'll work on real features end to end, from API design in Django to interactive UI in Next.js, while also getting hands on experience integrating LLMs into production workflows. This is a hybrid role, so you'll be expected to work from our office a few days a week alongside the rest of the team. What You'll Do Build and maintain backend services and REST/GraphQL APIs using Django and Django REST Framework Develop responsive, performant frontend interfaces using Next.js and React Integrate LLM APIs (OpenAI, Anthropic, or open source models) into application features like chatbots, summarization tools, or search Design and optimize prompts, and experiment with techniques like RAG (retrieval augmented generation) and embeddings Work with vector databases (Pinecone, Weaviate, pgvector, etc.) for semantic search use cases Write clean, tested, maintainable code and participate in code reviews Collaborate with product and design teams to translate requirements into working features Debug and optimize application performance across the stack Stay current with LLM tooling, frameworks, and best practices as the space evolves What We're Looking For 1-2 years of professional experience with Django and Python in a production environment Solid working knowledge of Next.js, React, and modern JavaScript/TypeScript Hands on experience integrating LLM APIs or frameworks (LangChain, LlamaIndex, or direct API integration) Good understanding of REST API design principles and database fundamentals (MySQL preferred) Comfortable with Git and collaborative development workflows Practical understanding of prompt engineering concepts Strong problem solving skills and ability to work independently on assigned features Good communication skills and comfort working in person with the team a few days a week Nice to Have Experience with Docker and CI/CD pipelines Exposure to vector databases or embedding models Personal projects, open source contributions, or side projects involving AI/LLM tools Familiarity with async programming in Python (Celery, async views) Why Join Us Work directly on cutting edge AI powered products, not just maintenance work Mentorship from senior engineers, with real ownership over features early on Collaborative, in person culture that values learning and experimentation Competitive salary with growth opportunities as the team scales