AI Engineer I

Responsibilities:
Implement Gen AI solutions for medical report processing under senior engineer guidance.
Write and optimize prompts for LLMs to extract medical information and generate codes.
Assist in building RAG systems by implementing document processing and vector storage components.
Conduct experiments with different prompt strategies and model configurations.
Support model evaluation by implementing metrics and running comparative tests.
Contribute to data preprocessing pipelines for medical text and clinical documents.
Participate in code reviews and learn best practices for production Gen AI systems.
Help monitor and debug Gen AI models in development and staging environments.
Document implementation details and contribute to the technical knowledge base.
Collaborate with senior engineers on feature development and system improvements.
Learn healthcare regulations and medical coding standards through hands-on projects.
Requirements:
Bachelor's/Master's in Computer Science, AI/ML, or related field.
1-3 years of professional software development experience.
Strong programming fundamentals and eagerness to learn Gen AI technology.
Gen AI and LLM Basics:
Basic understanding of Large Language Models and their applications.
Familiarity with prompt engineering concepts and techniques.
Experience with OpenAI API, Anthropic API, or similar LLM services (coursework/personal projects acceptable).
Understanding of text embeddings and semantic similarity concepts.
Basic knowledge of transformer architecture and attention mechanisms.
Technical Skills:
Proficiency in Python with experience in data manipulation (pandas, numpy).
Familiarity with ML libraries (scikit-learn, transformers, basic PyTorch/TensorFlow).
Basic understanding of APIs, JSON, and data processing workflows.
Experience with version control (Git) and collaborative development.
SQL knowledge for data extraction and analysis.

Experience
1-3 yrs