Job Title : Gen AI Engineer

Experience : 6-8 Years

Location : Noida

Type : Full-time | Permanent.

Key Responsibilities :

• - Develop and fine-tune LLMs (GPT, Llama, Mistral, Falcon, Claude, etc.) for domain-specific applications.
• - Implement RAG pipelines using LlamaIndex, LangGraph, and vector databases (FAISS, Pinecone, Weaviate, ChromaDB) to enhance response accuracy.
• - Build AI-powered chatbots and autonomous agents using LangGraph, CrewAI, LlamaIndex, and OpenAI APIs.
• - Optimize and deploy generative AI models for real-time inference using cloud platforms (AWS, GCP, Azure) and MLOps tools (Docker, Kubernetes, MLflow).
• - Fine-tune models using LoRA, QLoRA, PEFT, and RLHF to improve efficiency and personalization.
• - Develop AI-driven workflows for structured reasoning and decision-making using CrewAI and LangGraph.
• - Integrate multi-modal AI models (text, image, speech) into enterprise solutions.
• - Implement memory and retrieval strategies for LLM-based systems using vector search and caching techniques.
• - Ensure AI models follow ethical AI guidelines, bias mitigation, and security best practices.

Required Skills :

• - Languages & Frameworks : Proficiency in Python, PyTorch, TensorFlow, JAX.
• - RAG & Vector Databases : Experience with LlamaIndex, LangGraph, FAISS, Pinecone, ChromaDB, Weaviate.
• - Chatbots & AI Agents : Hands-on experience with CrewAI, LangGraph, OpenAI, Hugging Face Transformers.
• - Model Fine-Tuning & Optimization : Knowledge of LoRA, QLoRA, PEFT, RLHF, Prompt Engineering.
• - MLOps & Deployment : Experience with Docker, Kubernetes, FastAPI, LangServe.
• - Cloud Platforms : Experience deploying AI applications on AWS, GCP, or Azure.