[Remote] Prompt Engineer (LLM Automation for Data Labeling & Localization)

Note: The job is a remote job and is open to candidates in USA. Innodata Inc. is building a team of prompt engineers to harness the power of LLMs to automate data annotation and human evaluation workflows. The role involves collaborating with cross-functional teams to design solutions and improve the efficiency of data labeling and translation processes.

Responsibilities

• Collaborate with data scientists, linguists, and localization experts to ensure accuracy and cultural relevance.
• Prototype and validate AI models to demonstrate initial feasibility, potential impact, and overall effectiveness.
• Design, develop, and implement prompts for data labeling and localization processes within software applications.
• Understand the current components of the software stack, use cases and problems and iterate on solutions leveraging a solid knowledge of data structures, data formats, and data modeling.
• Conduct user testing and feedback analysis to optimize prompt design for data accuracy and linguistic consistency.
• Analyze model performance using key performance indicators (KPIs) and metrics, ensuring that AI models meet customer acceptance criteria and deliver high-quality outputs.
• Communicate technical findings and solution strategies to both technical and non-technical stakeholders, including presenting model performance and actionable insights in a clear, accessible manner.
• Collaborate on data pipelines and workflows that integrate LLMs into automated systems, enhancing both the efficiency and effectiveness of data annotation tasks.
• Create guidelines and training materials for prompt usage in data labeling and localization projects.
• Stay informed on data labeling and localization industry trends and tools to enhance prompt engineering techniques.

Skills

• Deep understanding of LLMs (e.g. transformer-based architectures).
• Demonstrated experience programmatically using LLMs to automate data labeling, classification, localization and annotation tasks.
• Strong expertise in Python for NLU, for data processing & transformation, and for statistical analysis. Familiarity with JSON, Javascript or XML.
• Experience with popular frameworks and libraries, including TensorFlow, PyTorch, Jupyter, and other relevant AI/ML tools.
• Familiarity with APIs and platforms for working with LLMs (e.g., OpenAI, Hugging Face, etc.).
• Knowledge of localization best practices and cultural nuances for different languages and regions.
• Strong understanding of LLM evaluation metrics and the ability to assess model reliability, bias, and generalizability.
• Experience working with data pipelines, automation tools, and integrating models into production systems to ensure scalable, reliable solutions.
• A collaborative mindset with the ability to solve complex technical challenges and work independently as needed.
• Exceptional attention to detail and a commitment to delivering high-quality, reliable AI solutions.
• Appreciation for issues of Diversity, Equity, and Inclusion in AI.
• Bachelor’s degree or higher in Computer Science, Artificial Intelligence, Machine Learning, Linguistics, Localization or a related field.
• 2 years of prompt engineering / LLM fine-tuning, or related AI/ML roles.
• Familiarity with tools/platforms for annotation and human-in-the-loop workflows (e.g., Labelbox).
• Experience designing and automating data annotation workflows.
• Knowledge of data annotation and the challenges of scaling human-in-the-loop workflows.
• Familiarity with cloud platforms, containerization, and model deployment.
• Knowledge of another language.

Company Overview

• (NASDAQ: INOD) Innodata is a global data engineering company. We believe that data and AI are inextricably linked. It was founded in 1988, and is headquartered in Hackensack, New Jersey, USA, with a workforce of 5001-10000 employees. Its website is http://www.innodata.com.

Company H1B Sponsorship

• Innodata Inc. has a track record of offering H1B sponsorships, with 2 in 2024. Please note that this does not guarantee sponsorship for this specific role.