AI Engineer - Generative AI, LLM & RAGPosition Overview Build practical AI and Generative AI solutions that address real-world business problems, from prototype through production. This mid-level role focuses on developing scalable AI applications, integrating Large Language Models, building RAG-based solutions, and bringing AI capabilities into enterprise platforms.
You'll work with senior engineers, architects, data scientists, and business teams while contributing to AI-powered chatbots, virtual assistants, document processing, knowledge-management solutions, and other AI applications.
What You'll Do - Develop and implement AI/ML solutions using Python and modern AI/ML frameworks.
- Build Generative AI applications using Large Language Models (LLMs).
- Develop RAG-based applications using document processing, embeddings, vector databases, and semantic search.
- Integrate LLMs such as Azure OpenAI, OpenAI, AWS Bedrock, Google Gemini, or equivalent platforms.
- Develop AI-powered chatbots, virtual assistants, document summarization, classification, extraction, and knowledge-management solutions.
- Implement prompt engineering techniques and evaluate LLM responses for accuracy, relevance, and reliability.
- Build and integrate REST APIs and microservices to expose AI capabilities to enterprise applications.
- Work with structured and unstructured data and develop data-preparation and processing pipelines.
- Implement AI solutions using cloud services on Azure, AWS, or Google Cloud.
- Collaborate with senior engineers and architects to develop scalable and production-ready solutions.
- Participate in proof-of-concepts and rapidly evaluate emerging AI technologies.
- Develop unit tests, integration tests, and automated validation for AI applications.
- Monitor AI applications and troubleshoot performance, accuracy, and production issues.
- Follow enterprise standards for security, data privacy, responsible AI, and application development.
- Contribute to technical documentation, solution design, and knowledge-sharing activities.
Required Qualifications - 3-6 years of experience in software engineering, AI/ML, data science, or a related technology field.
- Strong hands-on programming experience with Python.
- Experience with Machine Learning and/or Generative AI applications.
- Practical experience working with LLMs and prompt engineering.
- Experience building RAG applications using embeddings and vector search.
- Knowledge of ML/AI frameworks such as PyTorch, TensorFlow, or Scikit-learn.
- Experience working with REST APIs and microservices.
- Experience with SQL and relational or NoSQL databases.
- Experience with at least one cloud platform: Azure, AWS, or Google Cloud.
- Familiarity with Git and CI/CD practices.
- Good understanding of software development lifecycle and Agile methodologies.
- Strong problem-solving and communication skills.
Preferred Qualifications - Experience with Azure OpenAI or OpenAI APIs.
- Experience with LangChain, LangGraph, LlamaIndex, or Semantic Kernel.
- Experience with vector databases/search platforms such as Azure AI Search, Pinecone, FAISS, or similar technologies.
- Knowledge of AI agents and agentic workflows.
- Experience with Docker and Kubernetes.
- Familiarity with MLOps/LLMOps concepts.
- Experience with AI evaluation, guardrails, and responsible AI.
- Experience working with enterprise data or regulated industries such as banking, financial services, or insurance.
Experience Level - 3-6 years of total technology experience.
- 2+ years of hands-on experience with AI/ML or Generative AI is preferred.
Role Expectations The Mid-Level AI Engineer should be able to independently develop well-defined AI features and applications, troubleshoot technical issues, and contribute to solution design. The engineer will work under the guidance of senior engineers/architects for complex architecture and enterprise-level decisions.
Technology Environment Languages: Python, SQL
AI/ML: Machine Learning, NLP, Generative AI, LLMs
GenAI: RAG, Prompt Engineering, Embeddings, Vector Search, AI Agents
Frameworks: PyTorch, TensorFlow, Scikit-learn, LangChain/LangGraph
Cloud: Azure / AWS / Google Cloud
LLM Platforms: Azure OpenAI, OpenAI, AWS Bedrock, Google Vertex AI
Data: SQL, NoSQL, Vector Databases, Document Stores
Engineering: REST APIs, Microservices, Git, Docker, CI/CD
