Artificial Intelligence Developer

Job description

Role & Responsibilities • Develop and maintain Python-based applications integrated with LLMs such as OpenAI, HuggingFace, Anthropic, and Ollama. • Build end-to-end RAG pipelines, including document ingestion, chunking, embeddings, retrieval, and vector search. • Develop GenAI application interfaces using React, Streamlit, Gradio, Vue, or similar UI frameworks. • Build and integrate REST APIs using FastAPI or Flask to connect AI backends with front-end applications. • Implement prompt engineering, LLM orchestration, and techniques to improve response quality and retrieval accuracy. • Work with vector databases such as FAISS, Pinecone, Qdrant, Chroma, or Weaviate. • Integrate AI capabilities into intuitive and responsive user experiences such as chatbots, AI assistants, dashboards, and document-based applications. • Implement authentication, session management, and application state management for interactive AI solutions. • Write clean, modular, testable, and well-documented Python code using engineering best practices. • Use Git, Docker, and CI/CD practices for application development and deployment. • Debug and optimize both LLM/backend performance and UI responsiveness. • Collaborate with product and UX teams to convert designs and requirements into functional AI-powered applications. Preferred candidate profile • 3+ years of professional Python development experience with strong hands-on application development. • Practical experience building LLM/GenAI applications, not just theoretical or POC-level exposure. • Strong hands-on experience with RAG, embeddings, vector search, and LLM integration. • Experience with frameworks such as LangChain, LangGraph, LlamaIndex, or similar. • Hands-on experience with at least one UI technology such as React, Streamlit, Gradio, Vue, or similar. • Strong backend/API experience with FastAPI or Flask and REST API development. • Experience with vector databases such as FAISS, Pinecone, Qdrant, Chroma, or Weaviate. • Good understanding of prompt engineering and LLM response evaluation/optimization. • Exposure to Docker, Git, CI/CD, unit testing, and clean/modular architecture. • Strong debugging, problem-solving, communication, and collaboration skills. • Preferred candidates will have experience building end-to-end GenAI applications combining Python + LLM/RAG + API + UI