CareerVedaInternship program
- Real-world AI Project Implementation
- LLM Application Development
- AI Model Optimization
- AI Research & Development
- Industry Mentorship Program
- Production Deployment Experience
← All programs
Industry-AlignedEnrolling Now100% Placement Assurance
PG Program in GEN AI
Master Generative AI and transform your career with cutting-edge skills. Learn to build intelligent applications using the latest AI models, LLMs, and automation technologies, through hands-on projects and a capstone application.
Next BatchJuly 11, 2026
Duration6 Months · Live Online
Industry Projects30+
EligibilityFreshers, Graduates, Experienced
What you’ll gain from this program
Our PG Program in GEN AI equips you with cutting-edge AI skills through hands-on projects and expert guidance.
Doubt Resolution
AI Hackathons & Challenges
Career Guidance & Mentorship
Expert-Led Masterclasses
Best Learning Resources
200+ Hrs On-Demand Content
300+ Hrs Interactive Sessions
Seasoned Industry Professionals
End-to-End Job Support
Round-the-Clock Assistance
Customized Curriculum Track
Skill Evaluation Tests
Real-Time Performance Analytics
Professional Community Access
Self-Paced Learning Options
Global Alumni Community
Mock Interview Training
Industry-Recognized Certificates
Advanced LMS Platform
PythonLLMsPrompt EngineeringRAGAgentic AI
PG Program in GEN AI curriculum
A comprehensive curriculum designed by AI experts to make you job-ready. Master Generative AI, Large Language Models, prompt engineering, and AI application development with hands-on projects.
📚 16 modules · learning roadmap
01Introduction to Generative AI
- What generative AI is and how it differs from traditional ML
- The model landscape: text, image, audio, video and code
- Foundation models and how they are trained
- Capabilities, limitations and failure modes
- Gen AI roles and career paths
- Industry trends and outlook
02Python Foundations for Gen AI
- Python essentials for AI development
- Working in notebooks and virtual environments
- NumPy and pandas for data handling
- Calling model APIs from Python
- Keys, environment variables and configuration
- Python foundations exercise set
03Deep Learning Essentials
- Neurons, layers and activation functions
- Forward pass and backpropagation
- Loss functions and optimisers
- Training, validation and overfitting
- PyTorch essentials
- First neural network project
04Natural Language Processing Foundations
- Text preprocessing and tokenisation
- Word embeddings and vector representations
- Sequence models and attention
- Text classification and sentiment analysis
- Named entity recognition
- NLP foundations project
05Transformers & Large Language Models
- The transformer architecture explained
- Self-attention and positional encoding
- How LLMs are pretrained and aligned
- Tokens, context windows and cost
- Open versus closed models compared
- LLM exploration exercise
06Prompt Engineering
- Anatomy of an effective prompt
- Zero-shot, few-shot and chain-of-thought
- Structured output and formatting control
- System, developer and user roles
- Prompt evaluation and iteration
- Prompt engineering project
07Building with LLM APIs
- Calling OpenAI, Anthropic and open models
- Streaming, temperature and sampling controls
- Function and tool calling
- Rate limits, retries and error handling
- Cost tracking and token budgeting
- LLM-powered application component
08Embeddings & Vector Databases
- Embeddings and semantic search explained
- Chunking and indexing strategies
- Vector stores: pgvector, Pinecone, Chroma
- Similarity metrics and retrieval quality
- Keeping embeddings fresh as data changes
- Embedding pipeline project
09Retrieval-Augmented Generation (RAG)
- Why RAG and when it beats fine-tuning
- End-to-end RAG architecture
- Retrieval, re-ranking and context assembly
- Grounding, citations and reducing hallucination
- Evaluating RAG answer quality
- RAG application project
10Fine-Tuning & Model Customisation
- When to fine-tune versus prompt or RAG
- Instruction tuning and dataset preparation
- Parameter-efficient fine-tuning with LoRA and PEFT
- Training, evaluation and iteration
- Deploying a customised model
- Fine-tuning project
11Image, Audio & Multimodal Generation
- Diffusion models and image generation
- Prompting and controlling image models
- Speech-to-text and text-to-speech
- Multimodal models with vision inputs
- Responsible use of generated media
- Multimodal generation project
12Agentic AI & Automation
- What makes a system agentic
- Tool use, function calling and planning
- Memory and multi-step reasoning
- Multi-agent orchestration patterns
- Guardrails and human-in-the-loop
- Agentic AI build project
13LLMOps, Deployment & Evaluation
- Packaging a Gen AI app as an API
- FastAPI and containerisation with Docker
- Prompt and output evaluation frameworks
- Monitoring, logging and cost control
- Safety, guardrails and content filtering
- Deployment project
14Responsible & Safe Gen AI
- Bias, fairness and harmful output
- Hallucination, grounding and verification
- Privacy, consent and data protection
- Prompt injection and security risks
- Governance, documentation and model cards
- Responsible AI review exercise
15End-to-End GenAI Application
- Problem Definition
- Data Collection & Preparation
- Model Development
- Deployment & Presentation
- End-to-End GenAI Application Demo
- Portfolio packaging of the capstone
16AI Career Readiness & Interview Prep
- Gen AI resume creation and optimization
- LLM and system design interview preparation
- Take-home build and case tests
- Behavioral interview training
- GitHub and LinkedIn portfolio for AI roles
- 1 year Placement Support for Top Fellows
Soft skills program
- Technical Communication Skills
- AI Project Presentation
- Collaborative Development
- Problem Solving & Critical Thinking
- Agile Methodologies
- AI Ethics & Responsible AI Practice
Ready to start PG Program in GEN AI?
Reserve your seat and a career expert will confirm your batch, fee and EMI options.