Prompt Engineer

This is a fully remote position, open to applicants in Canada.

📋 Description

• Create and execute prompt strategies to enhance accuracy, localization, and cultural relevance in data labeling and translation activities.

• Convert business needs into scalable AI-driven solutions alongside Product, Data Science, Operations, and client stakeholders.

• Discover automation possibilities and establish prompt-based workflows.

• Continuously assess and improve performance to guarantee quality and dependability.

• Work collaboratively with data scientists, linguists, and localization specialists.

• Prototype and validate AI models.

• Design, develop, and implement prompts for data labeling and localization within software applications.

• Comprehend software stack components, use cases, data structures, data formats, and data modeling to refine solutions.

• Perform user testing and feedback analysis to enhance prompt design.

• Evaluate model performance using KPIs and metrics in relation to customer acceptance criteria.

• Convey technical insights and solution strategies to both technical and non-technical audiences.

• Collaborate on data pipelines and workflows that integrate LLMs into automated systems.

• Develop guidelines and training resources for prompt usage.

• Keep track of industry trends and tools in data labeling and localization.

⛳️ Requirements

• Minimum of 2 years experience in prompt engineering / LLM fine-tuning, or related AI/ML positions.

• Knowledge of tools/platforms for annotation and human-in-the-loop workflows (e.g., Labelbox).

• Proven experience in designing and automating data annotation workflows.

• Understanding of data annotation and the challenges involved in scaling human-in-the-loop workflows.

• Familiarity with cloud platforms, containerization, and model deployment techniques.

• In-depth knowledge of LLMs, particularly transformer-based architectures.

• Proven track record of programmatically utilizing LLMs to automate tasks related to data labeling, classification, localization, and annotation.

• Strong proficiency in Python for NLU, data processing, transformation, and statistical analysis.

• Familiarity with JSON, JavaScript, or XML.

• Experience with TensorFlow, PyTorch, Jupyter, and other pertinent AI/ML tools.

• Knowledge of APIs and platforms for working with LLMs, including OpenAI and Hugging Face.

• Understanding of localization best practices and cultural nuances across different languages and regions.

• Strong grasp of LLM evaluation metrics and the capability to assess model reliability, bias, and generalizability.

• Experience in working with data pipelines, automation tools, and integrating models into production systems.

🏝️ Benefits

• Competitive salary and performance-based incentives.

• Opportunities for professional development and continuous learning.

• Flexible working hours and potential for remote work.

• Collaborative and innovative work environment.

• Health and wellness benefits.