Description

Design, build, and deploy LLM-based applications and deep learning models for NLP use cases.

This role is on-site.

Responsibilities

• Design, fine-tune, and deploy LLM-based applications using Python.
• Implement and optimize deep learning models for text classification, sentiment analysis, and summarization.
• Develop solutions using prompt engineering and vector databases for embedding storage and retrieval.
• Build AI-powered applications using Streamlit, FastAPI, and Flask.
• Deploy and scale ML models on Azure and GCP, supporting CI/CD pipelines.

Required Skills

• 6-8 years of overall experience in software development, data analytics, or data science.
• 2+ years of hands-on experience with deep learning, NLP, and Generative AI.
• Strong proficiency in Python and experience managing the AI model lifecycle.
• Experience with TensorFlow, PyTorch, and Hugging Face Transformers.
• Knowledge of orchestration frameworks like LangChain and agentic architectures (e.g., AutoGen).
• Experience deploying AI solutions on Azure or Google Cloud Platform (GCP).
• Bachelor's degree in a relevant field.

Preferred Skills

• Knowledge of healthcare domain workflows and data.
• Familiarity with multi-agent AI design patterns.

Key Skills

Education

Bachelor's degree