AI/ML

Job description

Key Responsibilities: ● Fine-tune and optimize LLMs such as LLaMA and OpenAI GPT using advanced prompt engineering and parameter-efficient techniques (LoRA, quantization). ● Design and implement end-to-end RAG pipelines with vector search (FAISS, hybrid retrieval, re-ranking). ● Build autonomous AI agents using LangChain and modern Agent Development Kits (ADK), including tool-calling, memory management, and multi-agent orchestration. ● Develop and optimize ML/DL models using PyTorch and TensorFlow, including multimodal architectures. ● Build scalable APIs using FastAPI/Flask and deploy AI systems on AWS/Azure. ● Implement guardrails, evaluation metrics, monitoring, and performance optimization for production AI systems. ● Containerize and manage deployments using Docker and Git. Required Qualifications: ● Strong proficiency in Python with solid understanding of Data Structures & Algorithms. ● Hands-on experience with PyTorch, TensorFlow, and Hugging Face Transformers. ● Experience building and fine-tuning LLMs (e.g., LLaMA, OpenAI GPT) including LoRA and quantization techniques. ● Strong experience in designing RAG pipelines and implementing vector search (FAISS, hybrid retrieval). ● Experience building AI agents with tool-calling, memory management, and orchestration (LangChain/ADK) ● Experience developing APIs using FastAPI or Flask. ● Working knowledge of SQL/MySQL, Redis, and cloud deployment (AWS/Azure). ● Familiarity with Docker, Git, and production deployment practices Tasks Fine-tune and optimize LLMs such as LLaMA and OpenAI GPT using advanced prompt engineering and parameter-efficient techniques (LoRA, quantization). ● Design and implement end-to-end RAG pipelines with vector search (FAISS, hybrid retrieval, re-ranking). ● Build autonomous AI agents using LangChain and modern Agent Development Kits (ADK), including tool-calling, memory management, and multi-agent orchestration. ● Develop and optimize ML/DL models using PyTorch and TensorFlow, including multimodal architectures. ● Build scalable APIs using FastAPI/Flask and deploy AI systems on AWS/Azure. ● Implement guardrails, evaluation metrics, monitoring, and performance optimization for production AI systems. ● Containerize and manage deployments using Docker and Git Requirements Strong proficiency in Python with solid understanding of Data Structures & Algorithms. ● Hands-on experience with PyTorch, TensorFlow, and Hugging Face Transformers. ● Experience building and fine-tuning LLMs (e.g., LLaMA, OpenAI GPT) including LoRA and quantization techniques. ● Strong experience in designing RAG pipelines and implementing vector search (FAISS, hybrid retrieval). ● Experience building AI agents with tool-calling, memory management, and orchestration (LangChain/ADK) ● Experience developing APIs using FastAPI or Flask. ● Working knowledge of SQL/MySQL, Redis, and cloud deployment (AWS/Azure). ● Familiarity with Docker, Git, and production deployment practices.