Description

Design and build NLP and LLM solutions, including RAG applications and inference pipelines, for business use cases.

This role is remote.

Responsibilities

• Build and fine-tune NLP/LLM models for classification, summarization, and Q&A tasks.
• Develop production-quality Python code for training, inference, and evaluation pipelines.
• Integrate LLM applications into services and APIs, ensuring scalability and reliability.
• Establish model evaluation, monitoring, and governance practices including safety and drift detection.
• Collaborate with data engineering and platform teams on deployments and CI/CD workflows.

Required Skills

• 6+ years of experience in software development, data science, or ML engineering.
• 2+ years of hands-on deep learning experience with NLP or GenAI.
• Strong Python proficiency with production-quality, testable code.
• Experience with PyTorch, TensorFlow, or Hugging Face Transformers.
• Understanding of deep learning architectures, tokenization, attention mechanisms, and fine-tuning.
• Experience building prototypes and APIs using FastAPI, Flask, or Streamlit.

Preferred Skills

• Experience with LLM orchestration frameworks like LangChain, LlamaIndex, or Semantic Kernel.
• Familiarity with vector databases (FAISS, Pinecone, Weaviate) and embedding workflows.
• Experience deploying ML/LLM workloads on cloud platforms, particularly Azure.

Key Skills

Education

Bachelor's degree