Requirement Details:

Position: 324130 Machine Learning Engineering Engineer 3 - Generative AI Engineer

Location: Dearborn, MI

Duration: Full time

Description: Employees in this role are responsible for designing, developing, and deploying cutting-edge Generative AI solutions, with a particular emphasis on Retrieval-Augmented Generation (RAG) systems. This involves leveraging various AI techniques, including vector databases and robust API development frameworks like FastAPI, and ensuring efficient deployment through containerization and MLOps practices, to build intelligent applications that enhance user experience and automate complex processes.

Responsibilities:

• Design, develop, and implement Generative AI models and applications, specifically focusing on building and optimizing RAG systems, including the integration and management of vector databases, using various technology stacks, with a preference for the OpenAI SDK.
• Apply fundamental Machine Learning concepts, including model fine-tuning, to improve the performance and accuracy of AI solutions, and deploy them via efficient APIs, such as those built with FastAPI, utilizing containerization for consistent environments.
• Perform data engineering tasks to prepare, process, and manage data pipelines essential for training, evaluating, and deploying Generative AI models, including data ingestion for vector databases, ensuring data quality and accessibility.
• Utilize advanced prompt engineering techniques to optimize interactions with large language models and achieve desired outputs, and expose these capabilities through well-designed APIs.
• Collaborate with cross-functional teams to integrate AI solutions into existing products and services, ensuring scalability, reliability, and maintainability on cloud platforms, particularly Google Cloud Platform (GCP), adhering to MLOps principles and continuous integration/continuous deployment (CI/CD) practices.

Skills Required: GCP, Big Data, Artificial Intelligence & Expert Systems, API

Skills Preferred: Google Cloud Platform

• Core: Python, SQL, GCP
• Frameworks & SDKs: FastAPI, OpenAI SDK
• Databases: Vector Databases
• Development & Deployment Tools: Git, Docker
• Infrastructure & Practices: CI/CD, MLOps

Experience Required:

• 8+ years of experience in software engineering with a focus on Generative AI, Machine Learning, or related AI fields.

Experience Preferred:

• Experience deploying AI/ML models into production environments at scale.
• Previous experience in a large enterprise or fast-paced technology environment.
• Strong understanding of Generative AI principles and architectures, including Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems.
• Proven experience in building and deploying RAG systems, including the use of **Vector Databases**.
• Proficiency in Python programming.
• Solid experience with SQL for data manipulation and querying.
• Hands-on experience with Google Cloud Platform (GCP) services relevant to AI/ML.
• Basic understanding and practical experience with Machine Learning model fine-tuning.
• Familiarity with data engineering concepts and practices.
• Expertise in prompt engineering techniques for interacting with LLMs.
• Experience with the OpenAI SDK.
• Experience developing robust APIs, preferably with **FastAPI**.
• Proficiency with **version control systems (e.g., Git)**.
• Experience with **containerization technologies (e.g., Docker)**.