AI Engineer

As an AI Automation Engineer, you will be responsible for developing and fine-tuning LLM-based models and AI agents for automation, reasoning, and decision-making. Additionally, you will build multi-agent systems that coordinate tasks efficiently and design prompt engineering, retrieval-augmented generation (RAG), and memory architectures. Your role will also involve optimizing inference performance and reducing hallucinations in LLMs, as well as integrating LLMs with APIs, databases, and external tools for real-world applications. You will implement reinforcement learning with human feedback (RLHF) and continual learning strategies, collaborating with research and engineering teams to enhance model capabilities. Key Responsibilities: - Develop and fine-tune LLM-based models and AI agents - Build multi-agent systems for task coordination - Design prompt engineering, RAG, and memory architectures - Optimize inference performance and reduce hallucinations in LLMs - Integrate LLMs with APIs, databases, and external tools - Implement reinforcement learning with human feedback - Collaborate with research and engineering teams - Utilize tools like Python, LangChain, LlamaIndex, Autogen, Hugging Face, etc. - Work with open-source LLMs such as LLaMA, Mistral, Falcon, etc. - Deploy LLMs with strong inference capabilities using frameworks like vLLM - Build multi-modal RAG systems - Use vector databases like FAISS and Chroma for retrieval-based systems - Fine-tune LLMs, downscale models, and optimize model inference - Familiarity with multi-agent systems, cognitive architectures, and autonomous AI workflows Qualifications Required: - Strong experience in Python, LangChain, LlamaIndex, Autogen, Hugging Face, etc. - Experience with open-source LLMs (LLaMA, Mistral, Falcon, etc.) - Hands-on experience in LLM deployments with strong inference capabilities using robust frameworks such as vLLM - Knowledge of vector databases (FAISS, Chroma) for retrieval-based systems - Experience with LLM fine-tuning, downscaling, prompt engineering, and model inference optimization - Familiarity with multi-agent systems, cognitive architectures, or autonomous AI workflows Please note that the job type is Full-time, Permanent with benefits including health insurance and provident fund. The work location is in person.,