Description

You will design and build scalable machine learning and Generative AI solutions in a production environment, focusing on LLM-based applications and document AI pipelines.

This role is on-site.

Responsibilities

• Develop and deploy ML and GenAI systems using Python, ensuring code is scalable and maintainable.
• Design and optimize prompt engineering strategies for large language models to improve application performance.
• Build document extraction, parsing, normalization, and chunking pipelines for structured and unstructured data.
• Implement embedding generation and vector similarity search solutions using vector databases.
• Integrate ML models with Vector DBs and MongoDB, managing tagging and labeling workflows.

Required Skills

• Expert-level proficiency in Python for ML/AI workloads.
• 10+ years of experience in software engineering or data science roles.
• Hands-on experience building end-to-end ML pipelines (data ingestion, model training, evaluation, fine-tuning, and deployment).
• Strong knowledge of Large Language Models (LLMs) and Generative AI frameworks.
• Experience with Vector Databases and implementing vector similarity search.
• Proficiency with MongoDB and database integration for ML systems.
• Experience with cloud deployment, preferably on Azure, and knowledge of CI/CD pipelines.
• Ability to write production-grade, deploy-ready code.

Preferred Skills

• Experience with AWS and broader Cloud Computing services.

Key Skills

Education

Any Graduate