GenAI Engineer

Responsibilities:

• Build and optimize RAG (Retrieval-Augmented Generation) and Agentic AI workflows using LangChain, vector databases (Pinecone, FAISS, ChromaDB), and embedding models.
• Implement LLM fine-tuning, prompt chaining, and response ranking to enhance generative AI performance.
• Develop and evaluate retrieval mechanisms using semantic search and vector similarity techniques.
• Benchmark model performance using BLEU, ROUGE, METEOR, BERTScore, and other LLM evaluation metrics.
• Deploy AI models in production environments (AWS, GCP, Azure) with MLOps best practices for monitoring and retraining.
• Stay updated on the latest advancements in LLMs, transformers, and multi-agent AI architectures, applying new techniques to improve AI-driven applications.

Requirements:

• Hands-on experience in Generative AI, RAG, and Agentic AI workflows, with expertise in LangChain, embedding models, and vector databases (Pinecone, FAISS, ChromaDB).
• Strong Python skills with experience in Hugging Face, PyTorch, TensorFlow, and scikit-learn for LLM fine-tuning and prompt engineering.
• Proficiency in benchmarking LLMs using BLEU, ROUGE, METEOR, and BERTScore, ensuring model quality and optimization.
• Experience in cloud-based deployments (AWS, GCP, Azure) and MLOps tools (MLflow, Weights & Biases, KubeFlow) for monitoring and retraining.
• Familiarity with containerized deployments (Docker, Kubernetes) and distributed computing (Ray, Spark) for scalable AI workloads.
• Strong problem-solving skills, with the ability to optimize LLM pipelines for latency, efficiency, and real-world applications.