Description

You will build and deploy generative AI solutions using RAG patterns to solve business problems.

This role is hybrid.

Responsibilities

• Design efficient chunking and indexing strategies to support accurate answer generation.
• Develop and deploy inference APIs using Langchain to AKS or function apps.
• Monitor production GenAI bots and improve response quality through prompt refinement and user feedback.
• Collaborate with product owners and data teams to define requirements and secure necessary datasets.
• Contribute to a reusable GenAI codebase while following MLOps and coding best practices.

Required Skills

• 5+ years of experience in Machine Learning and LLM advancements.
• Proficiency in Python and PySpark.
• Hands-on experience with Azure OpenAI, Azure AI Search, Langchain, and vector stores.
• Experience productionizing code through DevOps pipelines using Git and Jenkins.
• Proven experience as an ML Engineer focused on generative AI, prompt engineering, and RAG applications.
• Ability to translate business requirements into technical backlogs.
• Experience supporting production applications and continuously improving model accuracy.

Preferred Skills

• Experience with open-source LLMs.
• Experience using Databricks or Azure ML.
• Basic knowledge of React or equivalent UI frameworks.

Key Skills

Education

Any Gradute