Generative AI Engineering Intern

About the Role

We are looking for curious and motivated interns who want to build practical AI applications and solve real business problems. You will work with our engineering team on Generative AI, Retrieval-Augmented Generation (RAG), conversational AI, voice assistants, and intelligent document processing. The role involves hands-on coding, experimentation, testing, and integration—not just using AI tools to generate content.

What You Will Work On

• Generative AI applications: Integrate large language models into business applications using APIs and open-source models.
• RAG and knowledge assistants: Build pipelines for document ingestion, text extraction, chunking, embeddings, vector search, and answers grounded in source documents.
• Voice AI: Work on speech-to-text, text-to-speech, transcription, multilingual conversations, and voice-based assistants.
• AI agents and workflows: Connect AI applications with databases, APIs, and business tools through function calling and workflow automation.
• Document intelligence: Extract and validate structured information from PDFs, scanned documents, images, and other business files.
• Backend development: Build Python services and REST APIs to connect AI capabilities with web applications.
• Evaluation and improvement: Test accuracy, relevance, response time, and cost; identify failure cases and improve results.

Key Responsibilities

• Understand assigned requirements and translate them into working prototypes.
• Write readable, reusable Python code.
• Prepare and process structured and unstructured data.
• Develop prompts and validate model outputs against expected results.
• Integrate AI models, databases, and external APIs.
• Debug issues and document experiments, implementation steps, and findings.
• Use Git for version control and participate in code reviews.
• Handle customer data responsibly and follow project security requirements.
• Communicate progress, blockers, and questions clearly.

Requirements & Tech Stack

• Basic proficiency in Python, including functions, data structures, file handling, and debugging.
• Understanding of REST APIs, JSON, and SQL.
• Familiarity with the fundamentals of AI, machine learning, and large language models.
• Basic understanding of prompts, embeddings, and RAG.
• Ability to break down problems, research solutions, and learn independently.
• Good communication skills and willingness to work collaboratively.
• Prior professional experience is not required. Academic projects, personal projects, and demonstrable practical learning are welcome.

Good-to-Have Exposure

Experience with any of the following will be an advantage; proficiency in all of them is not expected:

• LLMs and orchestration: OpenAI APIs, Azure OpenAI, Gemini, Hugging Face, LangChain, LlamaIndex
• Search and RAG: PostgreSQL with pgvector, Qdrant, Azure AI Search
• Voice processing: Whisper, speech-to-text and text-to-speech APIs, audio processing
• Backend development: FastAPI, Flask, PostgreSQL
• Application development: JavaScript, React, Node.js
• Deployment and tooling: Git, Docker, Linux, Azure or AWS
• Document and image processing: OCR, PDF extraction, OpenCV

Qualifications

• Final-year students or recent graduates in Computer Science, Information Technology, AI/ML, Data Science, Electronics, or a related discipline.
• Candidates from other disciplines with strong programming fundamentals and relevant projects may also apply.
• Available for a six-month internship based in Bangalore.
• Interested in pursuing a long-term career in AI engineering.

What You Will Gain

• Hands-on experience building AI solutions for real business use cases.
• Exposure to the complete development lifecycle—from data preparation and prototyping to evaluation and deployment support.
• Technical guidance and code reviews from experienced team members.
• Practical understanding of the accuracy, latency, cost, and data-handling tradeoffs involved in AI applications.
• An opportunity to move into a permanent role based on performance.

Performance and Permanent Role Consideration

Performance will be assessed on: learning progress and technical understanding, quality and reliability of assigned deliverables, problem-solving and debugging ability, ownership, teamwork, and communication, ability to apply feedback and meet agreed timelines.

Candidates who demonstrate strong performance may be offered a permanent position after completing the internship. Compensation and terms for the permanent role will be discussed at that stage. Conversion is performance-based and is not guaranteed.

Selection Process

• Resume and project review.
• A short practical programming or AI assignment.
• Technical discussion covering fundamentals and submitted work.
• Final discussion on availability and role expectations.