Generative AI Engineer

Key Responsibilities:
Design and develop generative AI applications using LLMs (GPT, Claude, Gemini, LLaMA)
Implement RAG (Retrieval-Augmented Generation) pipelines for knowledge-based AI systems
Fine-tune and optimize LLMs for specific use cases and domains
Build prompt engineering frameworks and templates for consistent AI outputs
Integrate AI models with APIs, databases, and enterprise applications
Develop vector databases and embedding strategies for semantic search
Implement guardrails, security measures, and bias mitigation techniques
Monitor model performance, latency, and cost optimization
Collaborate with data scientists, ML engineers, and product teams
Stay updated on latest Gen AI research, models, and best practices
Required Skills:
Strong programming skills in Python
Experience with LLM APIs (OpenAI, Anthropic Claude, Google Gemini)
Knowledge of prompt engineering and chain-of-thought reasoning
Familiarity with LangChain, LlamaIndex, or similar frameworks
Understanding of RAG architecture and vector databases (Pinecone, Weaviate, ChromaDB)
Experience with embeddings and semantic search
Knowledge of transformer architecture and attention mechanisms
REST API development and integration
Git version control
Preferred Skills:
Experience with fine-tuning LLMs (LoRA, QLoRA)
Knowledge of AI safety, alignment, and responsible AI practices
Cloud platforms (AWS, Azure, GCP) for AI deployment
Docker and Kubernetes for containerization
MLOps and CI/CD pipelines
Experience with agent frameworks (AutoGPT, LangGraph)