Description

Responsibilities:
· GenAI use cases requirements understanding working with product owners, business and
design LLM solutions aligned with approved RAG patterns
· Drive data requirements conversations and work with data office to get required data for the use case
· Design efficient chunking & indexing strategies to support answer generation as per expectations
· Develop and deploy inference APIs using frameworks like langchain and deploy to AKS or function apps
· Capable to pick up UI work as needed to support front end integration collaborating with UI team
· Support GenAI knowledge BOTs in production by monitoring user feedback and improve BOT response quality through enhancements as per feedback
· Embrace best practices, processes related to MLOps, Coding best practices
· Experience in optimizing model accuracy by efficient prompt refinements
· Collaborate with existing members in the team, contribute to reusable GenAI code base


What we are looking for:
· Minimum of 5 years of experience solving high-impact business problems using Machine learning & latest advancements in LLMs
· Proven experience as a ML Engineer, with a strong focus on generative AI, prompt engineering, and RAG applications.
· Hands-on experience using Azure AI search, Langchain, other Vector stores. Experience in Azure OpenAI. Open-source LLMs is a plus.
· Strong software development skills with proficiency in Python, Pyspark, preferably using Databricks Azure ML. Basic knowledge of React or equivalent UI frameworks is a plus.
· Strong experience in supporting production applications post development and continuously improve response quality to increase benefits
· Strong collaboration skills, ability to translate sophisticated requirements into technical backlog, presentation skills, and an ability to balance a sense of urgency with shipping high-quality and pragmatic solutions.
· Experience in productionizing code through the DevOps pipeline (git, Jenkins pipeline, code scan).

Education

Any Gradute