Job Description
About the company
Chubb is the world’s largest publicly traded property and casualty insurer. With operations in 54 countries, Chubb provides commercial and personal property and casualty insurance, personal accident and supplemental health insurance, reinsurance, and life insurance to a diverse group of clients. The company is distinguished by its extensive product and service offerings, broad distribution capabilities, exceptional financial strength, underwriting excellence, superior claims handling expertise and local operations globally.
Location: Bangalore, India
Job Description
We are seeking a skilled AI Engineer with a strong background in prompt engineering for large language models (LLMs). The ideal candidate will have experience in designing and maintaining LLM driven applications.
Key Responsibilities
- Prompt Engineering
- Design, develop and optimize prompts for large language models to achieve desired business outcomes.
- Experiment with different prompt structures and parameters to improve LLM output performance.
- Continuously evaluate and refine prompts based on business feedback and model performance metrics.
- Business and Stakeholder Management
- Leadership and Collaboration
- Research and Innovation
- Stay update with the latest advancements in LLMs, NLP and LLMOps.
- Conduct Research to explore new prompt engineering techniques and best practices.
- Develop in depth understanding of ethical AI and responsible AI practices.
- Model Guardrails and Performance Monitoring
- Conduct thorough evaluations and tests to validate the performance, accuracy, and efficiency of language models.
- Implement fallback mechanisms to handle cases where the model’s output is uncertain or less relevant.
- Implement content moderation functionalities to detect and block harmful content and have a system in place for reviewing it in a timely manner.
- Regularly audit the LLM outputs to identify and mitigate inherent biases.
- Gain deeper understanding of Chubb’s business and develop expertise on multiple lines of business.
- Work with business partners globally to define the scope of the project, determine analyses to be performed, manage deliverables against timelines, present of results and implement the model.
- Handle stakeholder requests and perform work with little to no assistance.
- Be a thought leader and generate ideas / novel approaches to business problems.
- Mentor and coach junior team members and provide support on projects requiring advanced skill and domain expertise.
- Collaborate with NLP Engineers and Data Scientists to integrate LLM solutions into business applications.
- Ensure human oversight for critical applications where model outputs can have significant impacts on the business outcomes.
Requirements
- Bachelor’s degree in computer science, Engineering, Statistics, Math, or related quantitative fields. Advanced degree (e.g., master’s or PhD) in Computer Science, Engineering, or a related field, with a focus on NLP or machine learning would be an add-on.
- Minimum 3 years of hands-on experience in data analytics fields is preferred.
- Hands-on experience in Python and familiarity with relevant frameworks and libraries such as TensorFlow, PyTorch, or Hugging Face.
- Solid understanding of traditional machine learning algorithms as well as deep learning models like BERT and Transformers, in the context of LLMs. ML concepts - Probabilistic Models, Supervised vs Unsupervised Learning, Ensemble Techniques, Hyperparameter Optimization, and Deep Learning; Strong experience in developing and maintaining machine learning models.
- Must have experience with GitHub and RESTful APIs.
- Strong communication and presentation skills to effectively collaborate with cross-functional teams and communicate complex technical concepts.
- Ability to handle and prioritize multiple tasks and draw risk related insights from large datasets to aid business decision.
- Should be adept at research and must look to apply new methodologies to varied situations.
- Previous exposure to/ knowledge of insurance industry will be an added advantage.
- Good understanding of NLP concepts, including text classification, named entity recognition, sentiment analysis, and language modelling.
- Familiarity with model optimization techniques, including quantization and compression for deployment in resource-constrained environments.
- Knowledge of R/SQL, Big data technologies and working experience with JIRA is an added plus.
