Description

You will build and deploy LLM-based applications for legal text processing and drive new product development.

This role is on-site.

Responsibilities

• Develop, fine-tune, and deploy large language models for legal text tasks.
• Design pipelines for preprocessing, annotating, and managing large-scale NLP datasets.
• Prototype ideas and conduct experiments to evaluate model performance.
• Implement coding best practices, code reviews, and development processes.
• Collaborate with product designers and engineers to translate requirements into software designs.

Required Skills

• Strong Python background with experience writing production code.
• Practical experience with NLP libraries: spaCy, word2vec, Flair, and BERT.
• Deep learning expertise using PyTorch, TensorFlow, and Keras.
• Experience with LLMs, prompt engineering, fine-tuning, and benchmarking using LangChain or LlamaIndex.
• Formal training in machine learning including dimensionality reduction, clustering, embeddings, and sequence classification.
• Proficiency with relational/NoSQL databases and vector stores (Postgres, Elasticsearch/OpenSearch, or ChromaDB).
• Knowledge of cloud platforms: AWS, GCP, or Azure.
• Understanding of data modeling principles and complex data models.

Preferred Skills

• Knowledge of Scala, Spark, Ray, or other distributed computing systems.
• Experience with API development, containerization, and machine learning deployment.

Key Skills

Education

Bachelor's degree