AI Engineer (LLM | RAG | Azure AI)
ICONMA
Our client, a IT Services and Consulting company, is looking for I Engineer (LLM | RAG | Azure AI) for their Middletown, NJ/Dallas, TX/Atlanta, GA location.
Responsibilities:
Design, develop, and integrate Gen AI-powered applications using large language models and related AI services
Build solutions involving prompt engineering, retrieval-augmented generation, embeddings, vector search, and AI agents
Develop APIs, services, and application components that connect Gen AI capabilities to business workflows
Work with structured and unstructured data to support knowledge retrieval, summarization, classification, and content generation use cases
Evaluate model performance, response quality, hallucination risk, and reliability across different scenarios
Collaborate with product, data, engineering, and architecture teams to deliver scalable AI solutions
Implement responsible AI practices including security, privacy, monitoring, explainability, and governance considerations
Support deployment and release processes using tools such as Azure DevOps, Git, CI/CD pipelines, and cloud environments
Create documentation, reusable patterns, and technical guidance for Gen AI solution development
Stay current with emerging Gen AI frameworks, model capabilities, and best practices
Requirements:
5-10 years in Software Engineering, Machine Learning, AI Engineering, or Data Engineering.
3+ years of hands-on experience building and deploying Generative AI/LLM applications.
Experience delivering enterprise-scale AI solutions in production environments.
3+ years of software engineering, data engineering, machine learning, or AI application development experience
Hands-on experience building applications with large language models
Experience with prompt engineering, RAG architectures, embeddings, and vector databases
We are seeking a Gen AI Engineer to design, build, and deploy generative AI solutions that support enterprise applications, automation, knowledge discovery, and intelligent user experiences. The ideal candidate will have hands-on experience working with large language models, prompt engineering, retrieval-augmented generation, model evaluation, and application integration. Experience with Azure DevOps is helpful for supporting deployments, CI/CD workflows, and collaboration with engineering teams, though this role is not primarily DevOps-focused.
Proficiency in Python and familiarity with APIs, microservices, or backend development
Experience working with cloud-based AI services, preferably on Azure
Understanding of model evaluation, testing, monitoring, and quality improvement techniques
Familiarity with secure development practices and enterprise application integration
Strong problem-solving, communication, and collaboration skills
Experience with Azure Open AI Service, Azure AI Search, Azure Machine Learning, or related Azure AI services
Working knowledge of Azure DevOps, including repositories, boards, pipelines, and release workflows
Experience with Agentic-LLM solutions using Lang Chain, Lang Graph, or similar tools
Experience with vector databases or search platforms such as Azure AI Search
Familiarity with containerization, CI/CD, and deployment automation
Experience supporting enterprise-scale AI solutions, chatbot platforms, knowledge assistants, or intelligent automation use case
Years of Experience: 10.00 Years of Experience
Skills:
Category Name Required Importance
Technical Skills I Yes 1
Technical Skills Software Engineering Yes 1
Why Should You Apply?
Health Benefits
Referral Program
Excellent growth and advancement opportunities