Description

You will build and deploy scalable machine learning and generative AI systems, focusing on LLM applications, document AI pipelines, and vector search implementations.

This role is on-site.

Responsibilities

• Develop production-grade Python code for ML/AI workloads, ensuring scalability and maintainability.
• Design and optimize prompt engineering strategies for large language model applications.
• Build document extraction, parsing, normalization, and chunking pipelines for structured and unstructured data.
• Implement embedding generation and vector similarity search solutions using vector databases and MongoDB.
• Manage the end-to-end ML lifecycle, including model training, evaluation, fine-tuning, and deployment via CI/CD.

Required Skills

• Expert-level Python development for ML/AI workloads.
• Hands-on experience with Generative AI systems, LLMs, and prompt engineering.
• Proficiency in document AI pipelines: OCR, extraction, parsing, and text chunking.
• Experience with embedding generation, semantic search, and vector similarity search.
• Strong knowledge of Vector Databases and MongoDB for ML model integration.
• Experience with CI/CD pipelines and cloud deployment (Azure preferred).
• 10+ years of experience in data science or machine learning engineering.
• Ability to write production-ready, scalable code, not just theoretical or academic models.

Preferred Skills

• Experience with Azure Machine Learning.

Key Skills

Education

Any Gradute