Python Developer – NLP & LLM Focus

We are seeking a highly analytical and solution-oriented Python Developer with a strong background in data science and large language models (LLMs). The ideal candidate will possess deep expertise in troubleshooting complex issues and developing robust, scalable solutions. This role requires a blend of software engineering and data science skills in Natural Language Processing (NLP), with an emphasis on document text extraction, model execution, optimization, and implementation in production environments. Responsibilities: Design, develop, and deploy Python-based solutions to accurately extract and normalize information from documents Use cloud-based text extraction models and LLMs from OpenAI and Anthropic Work with NLP models for language processing / data classification Evaluate / compare model output Troubleshoot issues in data pipelines and model performance, and implement effective solutions to address performance and accuracy issues Collaborate with cross-functional teams to understand requirements, design solutions, and deliver high-quality code. Ensure code quality, documentation, and maintainability across projects. Optimize existing models and systems for efficiency and scalability. Requirements: Minimum of 5 years of experience in Python with a focus on NLP 1 year of hand-on integration and model execution experience with LLMs from OpenAI and/or Anthropic Experience working with relational databases like PostgreSQL and no-SQL databases like MongoDB Engineering degree in Computer Science or equivalent Solid understanding of software development best practices and data pipeline design Experience with Git, CI/CD pipelines, and cloud deployment (AWS, or Azure). Strong problem-solving skills and ability to work in an agile environment. Excellent communication and interpersonal skills. Preferred Skills (Nice to Have): Experience working with text extraction models (e.g., OCR, NLP-based extractors). Experience implementing fuzzy (non-exact) matching logic using tools like OpenSearch or similar technologies. Familiarity with International Trade Documents and domain-specific data.