ARTIFICIAL INTELLIGENCE INTERN

About the Role

This internship places you on the applied AI team at Medinex Workforce. You will design structured prompts, integrate LLM APIs into production workflows, build automated text parsing pipelines, and evaluate model performance, learning how forward-thinking software teams build production-ready AI applications.

Key Responsibilities

• Integrate commercial and open-source LLM APIs (such as OpenAI, Anthropic, or Gemini) into backend Python applications
• Design, test, and optimize system prompts, few-shot prompts, and structured output schemas (JSON mode)
• Implement Retrieval-Augmented Generation (RAG) pipelines, text chunking strategies, and vector embeddings
• Build automated pipelines to extract structured entities and summaries from unstructured documents and transcripts
• Develop evaluation benchmarks and validation checks to test model outputs for hallucinations, consistency, and accuracy
• Integrate guardrails and fallback mechanisms to ensure safe and predictable model behavior
• Version prompt templates, scripts, and model experiments using Git and GitHub
• Share progress in a short daily check-in and attend weekly AI engineering reviews

Requirements & Tech Stack

• Proficiency in Python with a solid grasp of REST API calls, asynchronous execution, and data structures
• Hands-on experience calling LLM APIs programmatically and parsing structured JSON responses
• Strong understanding of prompt engineering techniques, context window limitations, and token economics
• Methodical problem-solving habits and patience when running iterative evaluations on model outputs
• Clear written English for crafting precise prompt instructions and technical documentation
• A laptop and a stable internet connection

Helpful but not required

• Familiarity with orchestration frameworks like LangChain, LlamaIndex, or LiteLLM
• Exposure to vector databases (such as Chroma, Pinecone, or FAISS)
• Basic understanding of fine-tuning concepts, embeddings, or transformer architectures
• A GitHub profile showcasing personal generative AI, chatbot, or LLM-powered projects

Qualifications

• Final-year students and recent graduates from B.Tech, B.E., BCA, B.Sc (CS/IT/Data Science), MCA, or related technical streams
• Self-taught developers who have built and deployed applied generative AI applications
• Freshers seeking production-level exposure to applied LLM engineering and prompt architecture
• Candidates available to commit full-time for the duration of the internship

Employment Type: Full-time internship

Duration: 1 to 3 months

Stipend: Up to INR 14,000 per month

Workplace Type: Remote

Location: India

Work schedule: Full-time, Monday to Saturday or as assigned by your reporting manager.