Generative AI Internship

Responsibilities: Design and implement generative AI features such as AI career coaches, resume builders, interview prep assistants, and internship recommendation chatbots. Build RAG (Retrieval-Augmented Generation) pipelines using LLMs (OpenAI, Gemini, open-source models) and vector databases (FAISS, Pinecone, Weaviate, or pgvector). Develop and fine-tune prompts, agents, and workflows using frameworks like LangChain, LlamaIndex, or custom orchestration layers. Integrate generative AI capabilities into web/mobile applications via APIs (Flask/FastAPI) and ensure low-latency, cost-effective inference. Work on multi-modal generation (text, code, images) and evaluation of output quality, safety, and relevance. Implement guardrails, content moderation, and hallucination reduction techniques for production use. Collaborate with full-stack and ML teams to deploy models on AWS EC2 / cloud and monitor usage, latency, and costs. Document experiments, write clear reports, and present findings to the founding team. Requirements: Strong programming skills in Python and familiarity with AI/ML libraries (transformers, LangChain, LlamaIndex, sentence-transformers). Solid understanding of LLM fundamentals: tokenization, embeddings, RAG, prompt engineering, function calling, and agent architectures. Hands-on experience with at least one generative AI project (academic, hackathon, internship, or personal) with code on GitHub. Basic knowledge of APIs, REST, and working with JSON/data pipelines. Good problem-solving skills, curiosity, and ability to work in a fast-paced startup environment.