Description

You build and maintain production-grade ML systems, from generative AI applications to scalable data pipelines.

This role is on-site.

Responsibilities

• Develop advanced Python solutions for ML and AI workloads, ensuring scalable and maintainable code.
• Design and implement end-to-end ML lifecycles, including model training, evaluation, fine-tuning, and labeling workflows.
• Build Generative AI systems and optimize prompt engineering for large language models.
• Create Document AI pipelines for OCR, extraction, parsing, normalization, and text chunking.
• Implement embedding generation pipelines and vector similarity search using vector databases and MongoDB.

Required Skills

• 5+ years of experience in Python development.
• Strong understanding of LLM-based application development and prompt engineering.
• Experience with CI/CD pipelines and cloud deployment, preferably on Azure.
• Proficiency with MongoDB and Vector Databases for semantic search and retrieval.
• Ability to integrate ML models into production environments.

Key Skills

Education

Any Gradute