Machine Learning Engineer – Generative AI and LAG Applications

Job description

A leading organization is seeking a Machine Learning Engineer to design, build, and support machine learning and generative AI applications. This position focuses on integrating machine learning capabilities into production systems, with strong emphasis on Python development, large language models, retrieval-augmented generation, cloud-based ML services, and solid software engineering practices.

Responsibilities

• Build and maintain machine learning applications that support business insights and product innovation
• Develop production-ready Python services and APIs to power AI and machine learning use cases
• Implement and support large language model workflows, including retrieval-augmented generation patterns
• Work with structured and unstructured data across relational and NoSQL environments
• Partner with data scientists, software engineers, and product teams to integrate ML capabilities into applications and services
• Evaluate model behavior, track performance, and support automation for model monitoring and lifecycle management
• Prepare and transform data for model development, including preprocessing and feature-related workflows
• Contribute to scalable engineering patterns for deploying and supporting AI-enabled systems in cloud environments
• Support practical use of generative AI frameworks and vector-based retrieval approaches
• Apply machine learning fundamentals to integrate, monitor, and improve model-driven applications

Required experience and skills

• 3 or more years of experience as a Machine Learning Engineer or in a closely related engineering role
• Strong Python programming skills with clear experience building production applications
• Hands-on experience with large language models and retrieval-augmented generation workflows
• Experience with machine learning engineering workflows, including evaluation, performance tracking, and automation
• Strong software engineering fundamentals, including the ability to build APIs and application services from scratch
• Experience working in Google Cloud environments, including Vertex AI
• Experience with SQL and relational databases
• Experience with BigQuery and NoSQL databases such as MongoDB
• Familiarity with generative AI frameworks such as LangChain or Hugging Face
• Understanding of vector database concepts used in retrieval-based AI systems
• Knowledge of machine learning concepts, model integration, and operational workflows
• Experience with cloud platforms such as Google Cloud or Azure
• Ability to work effectively in cross-functional teams with strong problem-solving and communication skills

Preferred experience and skills

• Experience with agent-based or agentic application workflows
• Familiarity with Azure OpenAI
• Experience with natural language processing
• Exposure to distributed or large-scale data technologies such as Apache Spark or Ray
• Familiarity with streaming technologies such as Apache Kafka or PubSub
• Experience using version control tools such as Git
• Background in regulated or healthcare-related AI environments is helpful

FAQ

1. What are the primary responsibilities of a Machine Learning Engineer specializing in Generative AI and RAG applications?

A Machine Learning Engineer designs, builds, deploys, and maintains intelligent applications powered by Generative AI and Retrieval-Augmented Generation (RAG). The role focuses on integrating large language models (LLMs) with enterprise data sources, developing scalable AI pipelines, optimizing model performance, and delivering secure, production-ready AI solutions.

2. What is Retrieval-Augmented Generation (RAG), and why is it important?

Retrieval-Augmented Generation (RAG) combines large language models with external knowledge sources to generate more accurate, relevant, and context-aware responses. By retrieving information from trusted documents or databases before generating an answer, RAG helps improve response quality, reduce hallucinations, and support enterprise knowledge management.

3. How does this role contribute to Generative AI initiatives?

The engineer develops AI-powered applications such as intelligent chatbots, virtual assistants, document search platforms, content generation systems, summarization tools, and question-answering solutions. They integrate LLMs with enterprise workflows to improve productivity, automation, and decision-making.

4. What role does machine learning infrastructure play in this position?

Machine learning infrastructure supports the complete AI lifecycle, including data ingestion, feature engineering, model training, inference, deployment, monitoring, and continuous improvement. Engineers build scalable platforms that enable reliable and efficient AI operations in production.

5. How are enterprise data sources integrated into AI applications?

Machine Learning Engineers connect AI systems with structured and unstructured data repositories, document management systems, APIs, vector databases, and cloud storage. These integrations enable AI models to retrieve relevant business information and generate accurate, context-aware responses.