Job Title: Generative AI/ML & LLM Expertise
Location: Richardson, TX
Duration: 12+ Months
Required Skills:
Key Qualifications:
Proficiency in Python programming.
Expertise in Langchain, Autogen & langsmith for advanced API interactions and large-scale data processing.at production level
In-depth knowledge of Hugging Face's transformer models and libraries.
Experience in developing and deploying applications with FastAPI and Websockets
Specialized understanding of Generative Large Language Models (LLMs) and their applications.
Responsibilities:
Generative AI/ML & LLM Expertise:
Employ Autogen and Langchain for sophisticated API interactions and to process large datasets.
Interpret flowcharts to understand and design AI-driven workflows.
Integrate Hugging Face and other generative AI models into various applications.
Apply concepts of Chain of Thought (COT), Tree of Thought (TOT), and ReAct (Response & Act) agents in generative tasks.
Understand and implement machine learning and generative modeling techniques
Utilize different prompting strategies to effectively communicate with generative AI models.
Work with deep learning frameworks such as PyTorch or TensorFlow for model training and inference.
Develop causal inference models to understand data relationships and generate predictive insights.
Leverage LLMs for analyzing log data, code review, correction, and generation.
Extract insights from structured data sources like Excel, BigQuery, and SQL using generative models.
Integrate LLMs into API functions for enhanced interactivity and automation in tasks such as form-filling.
Expose open source models like LLama2 as APIs for broader application use.
Ensure the security and integrity of prompts and input data in generative AI applications.