Agentic Artificial Intelligence Engineer Intern

About the Role

Veyrai is seeking a curious and technically enthusiastic Agentic AI Engineer Intern to work on real-world AI systems, evaluate intelligent agents, and improve the quality of AI-powered products. This internship focuses on investigating AI system behavior, evaluating multi-turn conversations, identifying hallucinations, testing agentic workflows, and enhancing the reliability of AI-powered experiences. You will explore product scenarios, experiment with LLMs, and contribute to building evaluation systems.

Key Responsibilities

• AI Product Intelligence & Testing
• Explore Veyrai's AI-powered features to identify bugs, usability issues, and unexpected AI behavior.
• Evaluate AI mock interviews, coding assessments, and system design experiences.
• Investigate response quality, latency, contextual understanding, and conversation consistency.
• Document reproducible issues with clear observations and evidence.
• Agentic AI & LLM Evaluation
• Test multi-turn AI conversations and follow-up reasoning.
• Identify hallucinations, context drift, and inconsistent responses.
• Experiment with prompts, context engineering, memory, and retrieval workflows.
• Evaluate AI agents, tool calling, and automated execution workflows.
• Help design evaluation datasets, benchmarks, and scoring rubrics.
• AI Engineering & Experimentation
• Work with Python and/or JavaScript/TypeScript.
• Explore LLM APIs, embeddings, RAG, and agent architectures.
• Understand tool calling, code execution sandboxes, and agent workflows.
• Experiment with AI evaluation techniques and automated testing pipelines.
• Collaborate on improving AI response quality and product reliability.
• Product Quality & Research
• Test signup, login, and user journeys.
• Evaluate audio/video interview setup and user experience.
• Identify UI inconsistencies, performance issues, and workflow failures.
• Share actionable recommendations with the engineering team.

Requirements & Tech Stack

• Strong curiosity about Artificial Intelligence and emerging technologies.
• Basic understanding of LLMs and generative AI.
• Familiarity with prompt engineering and AI tools.
• Basic programming knowledge in Python, JavaScript, or TypeScript.
• Understanding of APIs, JSON, and basic software development concepts.
• Analytical thinking and problem-solving abilities.
• Strong attention to detail and willingness to experiment.
• Good communication and documentation skills.

Good to Have

• Familiarity with RAG, embeddings, and vector databases.
• Understanding of AI agents and tool calling.
• Experience with ChatGPT, Claude, Gemini, Cursor, or GitHub Copilot.
• Basic knowledge of REST APIs, Git, and databases.
• Interest in LLM evaluation, AI benchmarking, and context engineering.
• Experience building small AI-powered projects.

What You Will Gain

• Hands-on experience working with real-world AI-powered products.
• Exposure to agentic AI architectures and LLM evaluation.
• Practical experience with multi-turn AI systems and tool calling.
• Opportunities to experiment with modern AI development tools.
• Direct exposure to product engineering and AI quality workflows.
• The opportunity to contribute to a growing AI startup.

Compensation

• ₹30,000 per month – Fixed Internship Stipend.

Application Process

As part of the application:

• Register on https://veyrai.world
• Explore the Veyrai platform and its AI-powered features.
• Complete one free AI mock interview OR share a genuine post about your Veyrai experience on LinkedIn/X with a proof screenshot.
• Submit your observations, suggestions, and any issues you discover along with your application.