Technical Architect - Agentic AI

Based in Hyderabad or Bangalore, this role is designed for an experienced Technical Architect with 12 to 16 years of expertise, focusing on AI/ML and OpenAI technologies. The successful candidate will have a strong background in developing Generative AI applications, including hands-on experience with Retrieval-Augmented Generation (RAG), large language model (LLM) chaining using LangChain, and prompt engineering. This position involves leading the design and development of scalable AI solutions, working closely with cross-functional teams, and driving innovation by leveraging cutting-edge OpenAI-powered models.

Key Responsibilities
Lead the architecture and design of scalable Generative AI projects, ensuring technical leadership and timely delivery of high-quality solutions. Develop GenAI-powered chatbots and virtual assistants using RAG techniques, and build AI agents with agentic frameworks such as langGraph and autogen. Write efficient, maintainable Python code focused on AI model development, utilizing OpenAI libraries and frameworks. Design RAG pipelines that handle data from both structured and unstructured sources. Integrate OpenAI models seamlessly into software applications and systems through APIs. Collaborate with data scientists, engineers, and product managers to translate business requirements into detailed technical specifications. Document technical details including models, algorithms, and best practices related to OpenAI implementations. Stay up to date with the latest advancements in OpenAI technologies and emerging trends. Contribute to proof-of-concept initiatives to assess the feasibility of new OpenAI solutions.

Required Qualifications
A minimum of 10 to 12 years of experience in AI/ML roles with a strong focus on OpenAI technologies is essential. Candidates should have 1 to 2 years of hands-on experience building Generative AI applications, including expertise in RAG, LLM chaining with LangChain, and prompt engineering. Over 5 years of experience in developing Python-based backend services, APIs, and orchestrators that manage tool invocation, context handling, and task decomposition is required. At least 1 year of experience in developing goal-oriented autonomous agents capable of planning, task decomposition, and invoking tools via APIs and actions is necessary. Candidates must have a minimum of 1 year optimizing Azure OpenAI models for performance and scalability. Experience integrating OpenAI models into software applications using OpenAI APIs for 1 to 2 years is also required. A proven background as a Data Scientist or AI Developer with solid machine learning and data science expertise is expected.

Preferred Qualifications and Benefits
This role offers the opportunity to work with state-of-the-art OpenAI technologies in a leadership capacity, contributing to innovative AI solutions within a collaborative environment. Candidates with experience in agentic frameworks like langGraph and autogen, as well as those skilled in optimizing Azure OpenAI deployments, will be highly valued. While specific benefits are not detailed, the position provides a platform to architect advanced OpenAI-powered solutions and lead technical teams in dynamic and growing tech hubs.

Key Skills
AI/ML, OpenAI, Generative AI, Python, Large Language Models (LLM), Retrieval-Augmented Generation (RAG), LangChain.

This position is ideal for a highly skilled AI professional seeking to architect and lead the development of advanced OpenAI-powered solutions in Hyderabad or Bangalore.