Design, develop, and iterate on prompts for various LLM applications (conversational AI, content generation, summarization, etc.).
Experiment with prompt formats, styles, and techniques to optimize LLM performance and output quality.
Analyze LLM-generated responses, identify biases or limitations, and implement mitigation strategies.
IRAD Research:
Identify and propose innovative IRAD projects that leverage LLMs to solve complex problems or explore new capabilities.
Conduct research, experiment with cutting-edge techniques, and develop prototypes for potential products or services.
Collaborate with researchers, engineers, and other stakeholders to advance the state-of-the-art in LLM applications.
Present research findings internally and externally, publish papers and contribute to the AI/ML community.
Team Collaboration:
Work closely with data scientists, machine learning engineers, and other prompt engineers to integrate prompts and research findings into the broader AI/ML pipeline.
Share knowledge and best practices with the team, mentor junior engineers, and contribute to a collaborative learning environment.
Requirements & Skills:
BA/BS degree in Computer Science, Linguistics, or a related field.
Strong understanding of NLP fundamentals (language models, text processing, tokenization).
Experience with Python programming and relevant NLP libraries (e.g., Hugging Face Transformers).
Proven track record of crafting clear, concise, and effective prompts for LLMs.
Experience conducting independent research, publishing papers, and presenting at conferences (preferred).
Demonstrated ability to identify and solve complex problems through innovative solutions.
Excellent communication and collaboration skills to work effectively with cross-functional teams.
A passion for AI research and a desire to push the boundaries of LLM capabilities.
Experience with reinforcement learning from human feedback (RLHF) techniques.
Familiarity with prompt engineering tools and frameworks.
Contributions to open-source NLP projects.
Strong understanding of research methodologies and experimental design.
