AI Engineering Intern

About the Role

We are looking for curious and hands-on AI Engineering Interns passionate about building applications using Large Language Models (LLMs), Speech-to-Text (STT), Text-to-Speech (TTS), and AI-powered digital avatars. You will work closely with engineering and product teams to experiment with emerging AI technologies, build prototypes, and develop production-ready features for our conversational AI platform. This is an opportunity to work on real-world AI products.

Key Responsibilities

• LLM Integration: Build applications using LLMs such as OpenAI GPT, Google Gemini, Claude, and open-source models.
• Voice AI: Experiment with and integrate Speech-to-Text (STT) and Text-to-Speech (TTS) technologies for natural, real-time voice conversations.
• AI Avatars: Explore and integrate AI avatar technologies for realistic, interactive digital human experiences.
• Conversational AI: Develop AI-powered conversational agents, role-play simulations, and intelligent virtual assistants.
• Prompt Engineering: Design, test, and optimize prompts, system instructions, and conversational workflows.
• Backend Development: Build APIs, integrate AI services, and develop backend components for AI-powered applications.
• Experimentation: Evaluate new AI models, frameworks, APIs, and tools, identifying opportunities to improve product capabilities, response quality, latency, and cost.
• Prototyping: Rapidly build functional prototypes and convert successful experiments into scalable product features.

Requirements & Tech Stack

• Strong programming fundamentals in JavaScript/TypeScript or Python.
• Basic understanding of LLMs, Generative AI, and prompt engineering.
• Hands-on experience using APIs from OpenAI, Gemini, Claude, or similar platforms.
• Familiarity with REST APIs, JSON, and backend development.
• Understanding of basic concepts in machine learning and NLP.
• Familiarity with Git/GitHub and collaborative development practices.
• Strong problem-solving skills and a willingness to learn new technologies.

Good to Have

Experience or familiarity with any of the following is a plus:

• LLM Frameworks: LangChain, LangGraph, LlamaIndex, Hugging Face.
• STT/TTS: Google Speech-to-Text, Deepgram, ElevenLabs, Azure Speech Services, or similar.
• AI Avatars: HeyGen, D-ID, Tavus, Simli, or similar avatar platforms.
• Voice AI Frameworks: LiveKit, Vapi, Pipecat, or real-time audio processing.
• AI Infrastructure: Google Cloud Vertex AI, AWS Bedrock, or Azure AI.
• Development Stack: Node.js, React.js, Express.js, MongoDB.

Note: You don't need to know all these technologies. We value hands-on experimentation, curiosity, and the ability to build things.

Who Should Apply?

We are looking for builders and problem-solvers who enjoy experimenting with technology, learning independently, and turning ideas into working products. Students pursuing B.Tech, B.E., M.Tech, MCA, or related degrees in Computer Science, Information Technology, or equivalent disciplines are encouraged to apply.

Most importantly, show us something you have built! Personal projects, GitHub repositories, hackathon projects, and AI experiments will be given significant weightage.