Associate AI Full Stack Engineer

About the Role

We're building GenAI-powered applications that combine large language models, retrieval systems, and cloud-native infrastructure. We're looking for early-career engineers who have a strong grasp of AI/NLP fundamentals and full-stack development basics, and are eager to grow into building production-grade AI applications.

Responsibilities

• Assist in building and integrating RAG pipelines and LLM-powered features
• Develop front-end interfaces using React under guidance from senior engineers
• Build and maintain backend APIs using Node.js/Python
• Work with vector databases and LangChain for retrieval-based features
• Support deployment and testing of AI workloads on AWS
• Learn and follow team practices for code quality, version control, and testing
• Collaborate with product, design, and QA, and communicate progress/blockers clearly

Requirements

• Proficiency in Python
• Understanding of NLP basics: tokenization, text preprocessing, POS tagging, NER
• Text vectorization concepts: BoW, TF-IDF, Word2Vec/embeddings — should be able to explain and implement
• Conceptual understanding of transformer architecture (self-attention, positional encoding)
• High-level understanding of how LLMs (GPT/LLaMA-class models) work
• Exposure to RAG concepts and vector databases (FAISS or ChromaDB) — academic or personal projects acceptable
• Basic hands-on experience with LangChain (document loaders, text splitters, simple chains)