AI/ML Intern

• Strong Python programming skills
• Knowldge with vector DBs like Qdrant, Chroma, FAISS, or similar
• Familiarity with LLM frameworks (e.g., Hugging Face Transformers, LangChain, Ollama, llama.cpp)
• Knowledge of running models locally using GPU/CPU and optimizing inference
• Understanding of embedding generation, cosine similarity, and text chunking
• Experience with local server setup (Docker or bare-metal)
• Install, configure, and manage vector databases (e.g., Qdrant, ChromaDB, Weaviate) on local servers
• Generate and store embeddings using local or open-source embedding models
• Set up and integrate local LLMs (e.g., LLaMA, Mistral, GPT4All, Ollama) with vector DBs for RAG (Retrieval Augmented Generation)
• Build and test pipelines for ingesting text (e.g., PDFs, DOCX, websites) into vector stores
• Design simple APIs or UI interfaces for querying data via LLMs
• Monitor performance, latency, and memory usage of local models and databases
• Document all work including architecture diagrams, data flow, and configuration details

  Role & responsibilities

Preferred candidate profile