Generative AI Engineer

About the Role :

Ascendion is seeking an experienced and highly skilled Generative AI Engineer to join our innovative team. In this pivotal role, you'll be at the forefront of designing, developing, and deploying cutting-edge AI solutions, with a strong focus on Large Language Models (LLMs) and their applications. You'll work on complex problems, building robust RAG pipelines, integrating advanced OCR tools, and implementing intelligent agentic frameworks.

This is a hybrid role based in Bengaluru, Hyderabad, or Chennai, requiring a commitment to evening shifts (4 : 00 PM to 12 : 00 AM / 1 : 00 AM IST) to facilitate collaboration with global teams. If you have a passion for Generative AI, a strong background in Python, and a proven track record of delivering AI-powered solutions, we encourage you to apply.

Key Responsibilities :

- LLM Solution Development : Design, develop, and implement end-to-end solutions utilizing Large Language Models (LLMs) to address complex business problems.

- RAG Pipeline Construction : Build and optimize Retrieval-Augmented Generation (RAG) pipelines for enhanced LLM performance and context awareness.

- OCR Integration & Pre-processing : Integrate and work with various OCR tools such as Azure Doc Intelligence, Tesseract, or John Snow Labs. Implement and refine image pre-processing techniques (e.g., denoising, enrichment) within the OCR pipeline to improve data extraction accuracy.

- Framework & Platform Mastery : Leverage and implement solutions using advanced frameworks and platforms like Langchain, LlamaIndex, CrewAI, and Semantic Kernel.

- LLM Model Evaluation : Conduct systematic evaluation of LLM models to assess performance, accuracy, and bias, driving continuous improvement.

- Prompt Engineering : Apply advanced prompt engineering techniques to optimize LLM responses, control behavior, and achieve desired outcomes.

- Agentic Frameworks & Function Calling : Develop and integrate intelligent agentic frameworks, including Multi-Cloud Patterns (MCP), Agent-to-Agent (A2A communication), and Function Calling for complex task automation.

- Vector Search & Semantic Retrieval : Implement and optimize vector search capabilities, utilize embedding models, and develop robust semantic retrieval mechanisms for efficient information access.

- Python Programming : Write clean, efficient, and well-documented code primarily in Python for all stages of AI solution development.

- Azure AI Services : Work extensively with Azure AI Services, including Azure OpenAI, Azure AI Search, Azure AI Hub, and Azure Machine Learning Studio, to build and deploy AI solutions.

- Copilot Studio : Utilize Copilot Studio to develop and enhance AI-powered assistants and conversational interfaces.

What You Bring :

- Experience : 8+ years of professional experience in Artificial Intelligence, Machine Learning, or related fields, with a strong focus on Generative AI.

- LLMs & RAG : Proven experience in designing and implementing solutions using Large Language Models (LLMs) and building RAG pipelines.

- OCR Expertise : Hands-on experience with OCR tools (Azure Doc Intelligence, Tesseract, John Snow Labs) and image pre-processing techniques.

- Frameworks : Deep understanding and practical experience with LLM orchestration frameworks such as Langchain, LlamaIndex, CrewAI, or Semantic Kernel.

- Evaluation & Optimization : Experience with systematic LLM model evaluation and prompt engineering.

- Agentic AI : Familiarity with agentic frameworks, MCP, A2A communication, and function calling.

- Semantic Search : Strong knowledge of vector search, embedding models, and semantic retrieval techniques.

- Programming : Excellent proficiency in Python programming.

- Cloud AI Services : Practical experience with Azure AI Services (OpenAI, AI Search, AI Hub, ML Studio).

- Conversational AI : Experience with Copilot Studio is a plus.

- Collaboration : Ability to work effectively in a hybrid model and adapt to global shift timings.