Company
Stellantis logo

Stellantis

www.stellantis.com
Location

In office: Auburn Hills, United States

Apply

Prompt Engineer/Generative AI Engineer

As a Prompt Engineer/Generative AI Engineer, your role is to design, develop, refine, and optimize AI-generated text prompts to ensure they are accurate, engaging, and relevant for various applications. It includes natural language processing (NLP) models and prompts that drive the performance and effectiveness of language models and conversational AI systems. You will work with generative models and implement prompt engineering to create new and innovative AI products. You should possess experience in working with Large Language Models (LLMs), utilizing external models, and have the ability to fine-tune open-source models according to the specific requirements of our company. Collaboration with data scientists, machine learning engineers, and cross-functional teams will be crucial as you focus on creating high-quality prompts, refining model outputs, and enhancing the overall user experience. Your expertise in NLP algorithms, model engineering, and prompt engineering techniques will play a vital role in shaping the capabilities and performance of AI language models.

Key Responsibilities:

  • Prompt Engineering – Design and develop high-quality prompts and templates that guide the behavior and responses of language models. Craft prompts to elicit specific information or control the model’s output, ensuring desired accuracy, relevance, and language fluency. Optimize prompts to improve user interactions and system performance.
  • NLP Model Development – Design and develop NLP models, algorithms, and architectures to solve complex language understanding and generation problems. Apply state-of-the-art NLP techniques, including but not limited to text classification, named entity recognition, sentiment analysis, language modeling, and dialogue systems.
  • Data Analysis and Preprocessing – Analyze and preprocess textual data to prepare it for NLP model training and evaluation. Apply text cleaning, tokenization, normalization, and other techniques to ensure data quality and consistency. Handle challenges such as noisy or unstructured data, multilingual text, and domain-specific language.
  • Model Training and Evaluation – Train and fine-tune NLP models using appropriate algorithms and frameworks. Evaluate model performance using relevant metrics and datasets. Conduct experiments and analysis to improve model accuracy, efficiency, and generalization. Employ techniques like transfer learning and pretraining to leverage existing language models.
  • Performance Optimization – Optimize NLP models for speed, memory usage, and resource efficiency, enabling real-time or near-real-time responses. Explore techniques like quantization, model compression, and model distillation to reduce model size and inference latency. Collaborate with engineers to deploy and scale models in production environments.
  • Collaboration and Teamwork – Collaborate with data scientists, machine learning engineers, software engineers, and domain experts to understand business requirements and objectives. Work together to design and develop NLP solutions that address specific needs and enhance the user experience. Communicate effectively and contribute to a collaborative work environment.
  • Research and Innovation – Stay updated with the latest research advancements and trends in NLP. Explore and experiment with novel techniques, models, and approaches to solve challenging NLP problems. Publish papers, contribute to open-source projects, and participate in relevant conferences or communities.
  • Documentation and Communication – Document NLP model development processes, methodologies, and results. Clearly communicate complex NLP concepts, findings, and insights to technical and non-technical stakeholders. Present findings, recommendations, and progress reports to project teams and management.

Basic Requirements:

  • Bachelor degree in computer science, data science, artificial intelligence, or a related field. 
  • 5 years of experience in developing NLP models and systems, with a focus on prompt engineering or conversational AI
  • Strong programming skills in languages such as Python, with experience in NLP libraries/frameworks (e.g., NLTK, SpaCy, Transformers)
  • Deep understanding of NLP algorithms, techniques, and architectures, including text classification, sentiment analysis, named entity recognition, language modeling, and dialogue systems
  • Experience with machine learning frameworks (e.g., TensorFlow, PyTorch) and deep learning techniques for NLP
  • Proficiency in data preprocessing, text normalization, tokenization, and other NLP-specific techniques
  • Strong analytical and problem-solving skills,with the ability to formulate NLP solutions for complex language understanding and generation tasks
  • Familiarity with prompt engineering techniques and methodologies, including designing and optimizing prompts to control model behavior and outputs
  • Experience in training and fine-tuning NLP models using large-scale datasets and relevant evaluation metrics
  • Knowledge of performance optimization techniques for NLP models, such as model compression, quantization, and inference efficiency
  • Strong collaboration and communication skills to work effectively in multidisciplinary teams and present findings to stakeholders
  • Up-to-date knowledge of the latest research papers, advancements, and trends in NLP.
  • Experience with deploying NLP models in production environments and working with software engineering teams
  • Strong attention to detail, ability to work independently, and meet project deadlines
  • Publications in reputable NLP conferences or journals are advantageous
  • Fluent in English

Preferred Qualifications:

  • Advanced degree (Master’s or Ph.D.)