Job Description

AI Application Development

Intern (LLMs, RAG, TTS, GenAI)

Location: Bangalore, India

Job Type: Internship

Duration: 6 Months

Work Schedule: Day Shift

Work Mode: Onsite/In-person

About the Role:

We are seeking a passionate and curious AI Application Development Intern to join our team in building next-generation AI-powered solutions. This role is ideal for individuals enthusiastic about developing real-world applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Text-to-Speech (TTS), and Generative AI technologies. You will work closely with AI engineers, data scientists, and product teams to create intelligent applications such as AI Tutors, AI-powered ERP systems, and AI-enhanced Learning Management Systems (LMS).

Key Responsibilities

:

Develop and integrate LLM-based features into end-user applications using frameworks such as LangChain or LlamaIndex.

Design and implement Retrieval-Augmented Generation (RAG) pipelines for dynamic and contextual information retrieval.

Integrate and fine-tune Text-to-Speech (TTS) and Natural Language Processing (NLP) models for conversational experiences.

Collaborate with backend and frontend developers to create seamless user experiences in AI-driven applications.

Perform data preprocessing, feature engineering, and large-scale dataset management.

Evaluate and fine-tune pre-trained models (OpenAI, Mistral, LLaMA, Claude, etc.) for domain-specific use cases.

Monitor, test, and optimize model performance in real-world environments.

Stay current with trends and breakthroughs in Generative AI, open-source models, vector databases (e.g., FAISS, ChromaDB), and deployment frameworks (e.g., Docker, FastAPI, Streamlit).

Preferred Qualifications:

Proficiency in Python and familiarity with AI/ML libraries (NumPy, Pandas, Scikit-learn, TensorFlow, PyTorch, HuggingFace Transformers).

Hands-on experience or interest in working with Large Language Models (LLMs), RAG pipelines, and TTS models.

Understanding of NLP techniques including embeddings, tokenization, and context handling.

Familiarity with vector databases, API integration, and prompt engineering.

Exposure to cloud services (AWS/GCP/Azure) for AI model deployment.

Experience using version control systems (e.g., Git) and collaborative development workflows.

Strong analytical and problem-solving skills with attention to detail.

What You'll Gain

:

Real-World Project Experience: Contribute to building production-level AI-enabled apps for diverse industry use cases (education, healthcare, enterprise).

Mentorship & Guidance: Work alongside experienced AI engineers, software architects, and domain experts.

Portfolio Development: Create a portfolio of real-world projects that demonstrate your technical and problem-solving skills.

Career Development: Learn cutting-edge practices in AI model integration, RAG systems, LLM application architecture, and AI infrastructure.

Application Process

:

Send your resume and portfolio (if available) to: sales@yahwehsolutions.com

Shortlisted candidates will be invited for a technical discussion and interview.

For more information, contact: +91 8210856536

Job Type: Full-time

Pay: From ?5,000.00 per month

Schedule:

Day shift Monday to Friday
Work Location: In person

Speak with the employer

+91 9880910878