Company Description

Zenup Health is a mental health platform focused on providing expert therapy at affordable prices. The organization works with psychologists and psychiatrists who are committed to ethical practice and high-quality care. Zenup Health aims to create an inclusive space that supports a wide range of mental health needs for diverse individuals. The team also prioritizes building a structured, professional environment for mental health practitioners. Applicants will join a mission-driven company that values accessibility, ethics, and collaboration in mental health services.

Role Description

We are building an AI-powered therapy platform that leverages Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Knowledge Graphs, conversational memory, and evidence-based AI to assist therapists and users. As an AI/ML Intern, you will contribute to building intelligent, production-ready AI systems capable of understanding context, retrieving relevant knowledge, reasoning, and generating secure, personalized responses.

Responsibilities

- Develop and improve LLM-powered conversational AI systems.
- Design and optimize Retrieval-Augmented Generation (RAG) pipelines.
- Build and maintain Knowledge Graphs to enhance contextual reasoning and retrieval.
- Implement semantic search using embeddings and vector databases.
- Develop conversation memory systems for short-term and long-term personalization.
- Design prompt engineering and context management strategies.
- Build AI pipelines for emotion, intent, topic, goal, and risk detection.
- Improve AI response quality through evaluation, experimentation, and prompt optimization.




- Implement AI safety guardrails, hallucination detection, and response validation.
- Integrate speech-to-text and text-to-speech components where required.
- Build scalable AI backend services and APIs.
- Work closely with backend, frontend, and product teams to deploy AI features.

Required Skills

- Strong proficiency in Python.
- Solid understanding of Machine Learning, Deep Learning, and Natural Language Processing (NLP).
- Hands-on experience with Large Language Models such as OpenAI, Claude, Gemini, Llama, Mistral, or similar.
- Experience with prompt engineering and context optimization.
- Strong understanding of Retrieval-Augmented Generation (RAG).
- Experience with vector databases such as Pinecone, Qdrant, Weaviate, Chroma, or Milvus.
- Understanding of embeddings, semantic search, reranking, and retrieval techniques.
- Familiarity with Knowledge Graphs, GraphRAG, graph databases, and knowledge representation.
- Experience with LangChain, LangGraph, LlamaIndex, or similar LLM orchestration frameworks.
- Understanding of AI agents, tool calling, function calling, and multi-step workflows.
- Familiarity with conversational memory architectures, session management, and context persistence.




- Understanding of NLP tasks including emotion detection, intent classification, topic detection, entity extraction, summarization, and text classification.
- Knowledge of AI evaluation methodologies, hallucination detection, response scoring, and LLM benchmarking.
- Understanding of AI safety, guardrails, content moderation, and responsible AI practices.
- Experience building REST APIs using FastAPI or Flask.
- Working knowledge of PostgreSQL or similar databases.
- Familiarity with Git and collaborative software development.
- Experience with Hugging Face Transformers and Sentence Transformers.
- Experience with Redis for caching and memory management.
- Experience with speech technologies such as Whisper, Deepgram, AssemblyAI, or similar.
- Familiarity with evaluation frameworks such as LangSmith, Ragas, DeepEval, or OpenAI Evals.
- Experience with Docker, Kubernetes, and cloud platforms such as AWS, GCP, or Azure.
- Knowledge of fine-tuning techniques such as LoRA, PEFT, and adapters.
- Familiarity with asynchronous processing, queues, and scalable AI inference pipelines.
- Experience with AI observability, monitoring, and analytics.

Tech Stack

- Language: Python
- Backend: FastAPI
- LLMs: OpenAI / Claude / Gemini / Llama APIs
- Orchestration: LangChain / LangGraph / LlamaIndex
- Vector DBs: Pinecone / Qdrant / Weaviate / Chroma
- Knowledge Graphs: Neo4j
- Models: Hugging Face
- Version Control: Git

Pay: ₹7,000.00 - ₹10,000.00 per month

Benefits:

- Flexible schedule
- Paid sick time
- Paid time off
- Work from home

Work Location: Remote

📌 AI/ML Intern (India)
🏢 Zenup Health
📍 India