We're looking for an experienced LLM/NLP Engineer to help build the foundation of an innovative AI-driven platform. You'll play a central role in designing and deploying machine learning systems that transform raw documents into structured, actionable insights. Working alongside a focused team of engineers, product leads, and AI specialists, you'll contribute to the full ML lifecycle-from data preprocessing and model development to real-world deployment and performance optimization.
This is a rare chance to work on a greenfield product and influence the technical direction of an ambitious and fast-moving software initiative.
What You'll Do
Design, develop, and fine-tune LLM-based NLP models for tasks like document classification, entity recognition, and information extraction.
Build robust pipelines that include OCR, semantic embeddings, NER, encoder-only architectures, and semantic search to support a wide variety of document formats.
Partner closely with cross-functional teams to incorporate user feedback, refine outputs, and continuously improve model performance.
Stay current with state-of-the-art NLP research and integrate cutting-edge techniques into production-ready solutions.
What We're Looking For
Hands-on NLP experience: At least 2 years working directly with transformer-based models (e.g., BERT, GPT, LLaMa, etc.).
Strong technical foundation: Proficient in Python and PyTorch, with a deep understanding of ML tooling and development workflows.
Curious and engaged: Passionate about AI, actively follows new developments, and enjoys learning from the community.
Analytical mindset: Comfortable navigating complex problems and designing data-driven solutions.
Startup-ready: Thrives in a dynamic environment with shifting priorities and evolving product goals.
Team player: Communicates clearly and collaborates well across technical and non-technical teams.
