• Python
• GenAI
• LLM
• TensorFlow
• PyTorch
• Keras
• LangChain
• MLflow
• PromptFlow
• NLP
• BERT
• GPT-3/4
• T5
• RAG
• Prompt Engineering
• Fine-tuning
• Machine Learning

We are seeking a skilled Lead Software Engineer to spearhead a project focused on developing Generative AI applications using Large Language Models (LLMs) and Python. In this role, you will design, develop, test, and refine AI-generated text prompts to maximize their effectiveness across various applications.

You will collaborate with cross-functional teams to understand requirements, ensure prompts align with business goals and user needs, and integrate optimized prompts seamlessly into the overall product or system. You will rigorously evaluate prompt performance using metrics and user feedback, identifying areas for optimization and iteration.

The role requires deep expertise in prompt engineering principles and techniques such as chain of thought, in-context learning, and tree of thought. You will also document prompt engineering processes and outcomes, educate teams on best practices, and stay current on the latest AI advancements to bring innovative solutions to the project.

Strong experience with AI/ML frameworks like TensorFlow, PyTorch, Keras, LangChain, MLflow, and PromptFlow is essential, along with working knowledge of NLP and LLMs such as BERT, GPT-3/4, and T5. Knowledge of retrieval augmented generation (RAG) and the ability to fine-tune models is expected.