Talent.com
This job offer is not available in your country.
Ascendion - Artificial Intelligence Engineer - LLM

Ascendion - Artificial Intelligence Engineer - LLM

AscendionPune
30+ days ago
Job description

Job Summary :

Ascendion is seeking a highly skilled and passionate AI Engineer to join our innovative team. This role is pivotal in designing, developing, and deploying robust, scalable, and secure AI-powered solutions that leverage the latest advancements in large language models and cloud technologies. The ideal candidate will have strong backend development skills, hands-on experience with OpenAI APIs, and expertise in Azure cloud services. You will work on cutting-edge projects, contributing to solutions that drive significant business value for our diverse client base.

Key Responsibilities :

  • AI Solution Development : Design, develop, and implement end-to-end AI applications and services, primarily focusing on integrating Large Language Models (LLMs) like GPT-4o into business workflows.
  • Backend Engineering : Build and maintain scalable and efficient backend services using Python frameworks such as FastAPI or Flask to power AI applications and APIs.
  • Cloud Infrastructure Management : Deploy, manage, and optimize AI solutions on Microsoft Azure, utilizing services like Azure Functions for serverless compute, Azure Storage Account for data management, and Cosmos DB for NoSQL database needs.
  • API Development & Integration : Develop and consume RESTful APIs, ensuring secure data exchange and seamless integration with various systems using authentication mechanisms like OAuth and JWT.
  • Database Management : Work with NoSQL databases, specifically Cosmos DB, for efficient data storage and retrieval within AI applications.
  • DevOps & Deployment : Participate in setting up and maintaining CI / CD pipelines using Azure DevOps to ensure automated and reliable deployment of AI solutions.
  • Code Quality & Optimization : Write clean, well-tested, and maintainable code. Conduct thorough unit testing, debugging, and performance optimization to ensure high-quality and efficient AI applications.
  • Collaboration & Innovation : Collaborate closely with data scientists, machine learning engineers, product managers, and clients to understand requirements, translate them into technical solutions, and drive innovation.

Must-Have Skills :

  • Backend Development : Strong proficiency in Python, with hands-on experience in building robust web services using frameworks like FastAPI or Flask.
  • AI Integration : Practical experience integrating and utilizing OpenAI APIs, specifically with large language models such as GPT-4o, for various AI-driven functionalities.
  • Cloud Services : Demonstrated expertise in deploying and managing applications on Microsoft Azure, including Azure Functions (serverless compute), Azure Storage Account, and Azure Cosmos DB.
  • Database & Caching : Experience with NoSQL databases, particularly Azure Cosmos DB, for scalable and flexible data storage.
  • APIs & Authentication : Solid understanding and experience in developing and consuming RESTful APIs, along with implementing secure authentication mechanisms like OAuth and JWT.
  • DevOps & Deployment : Experience with CI / CD pipelines and tools, particularly Azure DevOps, for automated build, test, and deployment processes.
  • Code Quality : A strong commitment to writing high-quality code, including experience with unit testing frameworks, effective debugging techniques, and performance optimization.
  • Good-to-Have Skills :

  • Vector Databases for AI : Experience with Azure AI Search or other vector databases for efficient similarity search and retrieval in AI applications.
  • Logging & Monitoring : Familiarity with logging and monitoring tools like Application Insights and Azure Monitor for comprehensive application health and performance tracking.
  • Security : Knowledge of Azure Active Directory (AAD) and Role-Based Access Control (RBAC) for securing cloud resources and applications.
  • Retrieval-Augmented Generation (RAG) : Experience implementing RAG patterns with vector databases to enhance LLM responses with external knowledge.
  • LLM Orchestration : Hands-on experience with LLM orchestration frameworks such as LangChain or Semantic Kernel for building complex AI agent workflows.
  • Domain Experience :

  • Experience in OCR (Optical Character Recognition), Automation, Natural Language Data Analytics, and AI agents.
  • Experience in developing AI solutions for CRM, Personalization, Virtual Agents, and Self-service AI applications.
  • Work Hours :

    04 : 00 AM - 12 : 00 PM Pacific Standard Time (PST) - This implies early morning shifts for candidates located in India.

    ref : hirist.tech)

    Create a job alert for this search

    Artificial Intelligence Engineer • Pune