Founding AI Engineer Intern

Role Overview

Vetifi is building an AI-powered veterinary clinical intelligence platform designed to support symptom understanding, differential diagnosis, clinical questioning, emergency detection, diagnostic guidance, treatment information, prognosis, and prevention. We are looking for a Founding AI Engineer Intern who wants to work on a real AI product from an early stage and take ownership across the complete AI development lifecycle. This is not a basic chatbot or prompt-writing internship; you will work on structured veterinary knowledge, LLM pipelines, clinical reasoning, retrieval, scoring, evaluation, and production AI systems.

Responsibilities

• Build LLM and NLP pipelines for extracting structured knowledge from veterinary books.
• Develop clinical knowledge graphs, ontologies, and feature-value structures.
• Create source-grounded retrieval and response-generation systems.
• Build deterministic disease-ranking and clinical-scoring algorithms.
• Design intelligent follow-up question generation.
• Develop hallucination, omission, contradiction, and evidence-validation checks.
• Normalize veterinary symptoms, diseases, tests, treatments, and terminology.
• Build evaluation datasets and measure AI accuracy, completeness, and reliability.
• Integrate AI services with Vetifi’s backend and mobile applications.
• Experiment with embeddings, vector databases, graph databases, and different LLMs.
• Write scalable, reusable, well-tested Python code.
• Document technical decisions and contribute to the long-term AI architecture.

Requirements

• Strong Python programming skills.
• Experience working with APIs, JSON, data processing, and backend logic.
• Understanding of LLMs, NLP, machine learning, or information retrieval.
• Ability to independently build and debug working systems.
• Familiarity with Git and GitHub.
• Strong problem-solving ability and attention to detail.
• Ability to commit consistently for three months.

Skills

• Python
• LLMs
• NLP
• RAG
• Vector Databases

Nice to Have

• Experience with LLM APIs, structured output, function calling, or prompt engineering.
• Understanding of RAG, embeddings, vector databases, or semantic search.
• Experience with knowledge graphs, ontologies, Neo4j, RDF, or graph modelling.
• Familiarity with Pydantic, FastAPI, LangChain, LlamaIndex, or similar tools.
• Experience with model evaluation, hallucination detection, or AI guardrails.
• Interest in healthcare, veterinary medicine, biology, or clinical AI.

Internship Details

• Duration: 3 months
• Mode: Remote
• Commitment: Approximately 15–20 hours per week
• Stipend: Unpaid during the initial internship period
• Opportunity: High-performing candidates may be considered for a paid internship extension or full-time role.