• As an Junior Prompt Engineer have the opportunity to apply your deep expertise in LLM/GenAI technologies in solving real-world healthcare challenges.
• Your main responsibility will be collaborating closely with Drug Development teams to prototype, build, test, and deploy products powered by GenAI/LLM technology on a large scale.
• Design, test, and refine prompts to enhance the performance and accuracy of LLM outputs.
• Collaborate with senior engineers and product teams to understand use cases and align prompts with business goals.
• Conduct prompt evaluations and A/B testing to compare prompt effectiveness across different models
• Stay updated with advancements in prompt engineering, LLM capabilities, and emerging tools (e.g., LangChain, OpenAI APIs, Anthropic Claude).
• Maintain documentation of prompt experiments, results, and best practices.
• Accountable for deploying the generative AI solutions.
• Delivery of projects in close collaboration with platform and business teams

Education:

• Bachelor’s degree in computer science, Data Science, Machine Learning, or a related field.

Experience / Professional requirements

• Looking for fresh graduates who has completed multiple projects in NLP, machine learning, or AI development, with a focus on language models.
• Strong programming skills in Python, and experience with libraries such as TensorFlow, PyTorch, Hugging Face, or spaCy.
• Hands-on experience with deploying machine learning models into production environments (e.g., using Docker, Kubernetes, AWS, Azure).
• Familiarity with prompt engineering techniques and fine-tuning large language models.
• Knowledge of MLOps practices and tools for monitoring model performance.

• Customize pre-trained language models for specific use cases by fine-tuning them on domain-specific datasets.
• Curate, preprocess, and augment large datasets to improve the quality and generalization of language models.
• Design and optimize prompts to guide the model's responses for various tasks.
• Apply prompt tuning, zero-shot, and few-shot learning techniques to improve model accuracy.
• Deploy models in production environments, ensuring they meet performance and scalability requirements.
• Stay updated on industry trends, compliance, and responsible AI guidelines.

Preferred Skills:

• Experience with generative AI models, such as, GPT-4, AWS Bedrock Cludia or other LLMs.
• Experience working with APIs from OpenAI, Anthropic, or Hugging Face.
• Ability to think creatively and iteratively while debugging or optimizing prompts.
• Exposure to prompt chaining, RAG (Retrieval-Augmented Generation), or fine-tuning
• Familiarity with few-shot and zero-shot learning techniques
• Knowledge of cloud-based AI services and serverless architectures.
• Ability to work in an agile development environment and collaborate with cross-functional teams

• English