GEN AI Architect

Axtria; Hyderabad; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Axtria in Hyderabad, India, is seeking an experienced software engineer to develop Python-based applications on Azure, with a strong focus on Generative AI and large language models. You will design scalable architectures and work across modern web technologies to deliver robust AI-enabled solutions.

You will build and deploy GenAI systems using Langchain and RAG, perform model development and fine-tuning, and collaborate with cross-functional teams to integrate LLM components into products.

Qualifications

• 8–15 years of experience building Python applications on Azure.
• Hands-on Python and SQL experience.
• Strong knowledge of Generative AI and LLM concepts.
• Deep understanding of software architecture and web tech.
• Experience with Langchain, RAG, and prompt engineering.
• Familiarity with model development and fine-tuning.
• Ability to collaborate with cross-functional teams.
• Nice to have Databricks Genie.

Responsibilities

• Design and develop LLM-based systems and applications.
• Build and deploy Generative AI solutions for business needs.
• Develop models, fine-tune, and improve performance.
• Integrate LLM components into broader products.
• Advance prompts for higher accuracy and relevance.

Skills

Python

SQL

Azure

Generative AI

LLMs

Web technologies

Software architecture

Prompt engineering

Tools

Langchain

Databricks Genie

RAG

Job description

• Require 8-15 years experience to develop, test, and deploy Python based applications on Azure platforms
• Must have basic knowledge on concepts of Generative AI / LLMs / GPT
• Deep understanding of architecture and work experience on Web Technologies
• Python, SQL hands‑on experience
• Good to have Databricks Genie
• Design and develop LLM‑based systems:
• Build and deploy Generative AI solutions, often using frameworks like Langchain and techniques like Retrieval-Augmented Generation (RAG).
• Model development and fine-tuning: Train, fine‑tune, and refine large language models to meet specific business requirements or improve performance on particular tasks.
• Integration: Collaborate with cross-functional teams to integrate LLM models into broader applications and products.
• Prompt engineering: Develop and implement effective prompts to guide the LLM and improve the accuracy and relevance of its outputs.