You will be responsible for researching and developing AI-powered products that interact with ChatGPT or open-source AI models. Specifically:

Develop and Optimize AI Prompts

• Design and test effective prompts to improve AI model accuracy.
• Research and implement Prompt Engineering techniques to enhance AI-user interaction.
• Build specialized prompt libraries for various use cases such as customer support, internal assistance, and virtual assistants.

AI Integration with APIs or Self-Hosted Models

• Integrate ChatGPT API and AI models such as GPT-4, Claude, Llama, Mistral, etc., into internal systems.
• Deploy and optimize self-hosted AI models using open-source frameworks like Hugging Face and LangChain.
• Develop AI-powered chatbots and automated customer support systems.

AI Research & Optimization for Business

• Stay updated with the latest AI models and apply them to real-world products.
• Collaborate with product teams to integrate AI into internal workflows, such as report summarization, data analysis, and employee support.
• Ensure smooth AI operations, accurate responses, and compliance with data policies.

Must-have

• 1+ years of experience in AI (Machine Learning, NLP, Prompt Engineering, or Chatbot Development).
• Understanding of OpenAI APIs and how to call APIs from ChatGPT or other AI models.
• Proficiency in Prompt Engineering, with the ability to build and optimize AI prompt systems.
• Experience deploying open-source AI models such as Llama, Mistral, Whisper, Stable Diffusion.
• Strong programming skills in Python, FastAPI, LangChain, or similar frameworks.
• Basic English communication skills and ability to read technical documentation.

Nice-to-have

• Experience working with Hugging Face, OpenAI, Anthropic.
• Hands-on experience deploying AI models on servers or cloud platforms.
• Familiarity with Vector Databases (FAISS, Pinecone) and Retrieval-Augmented Generation (RAG).
• Experience with Docker, Kubernetes for AI model deployment.