GenAI Intern

Interon IT Solutions; Chantilly (VA); On-site; USD 34,000 - 55,000; Full time

Job summary

Interon IT Solutions in Chantilly, Virginia is seeking a hands-on Generative AI Engineer or GenAI Intern to develop AI-powered enterprise and healthcare products. You will work with product and engineering teams to move AI use cases from concept through prototyping, development, testing, deployment and continuous improvement.

The ideal candidate enjoys building real applications with LLMs, RAG, AI agents, APIs, and cloud technologies, not merely prompting.

Qualifications

• Bachelor's or Master's in Computer Science, AI, Data Science, SE, IT or related field.
• Strong Python programming skills; experience with REST APIs, JSON, databases, backend development.
• Understanding of Generative AI, LLMs, embeddings, prompt engineering, RAG, and AI app design.
• Experience or project exposure with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar frameworks.

Responsibilities

• Design, develop, test, and enhance Generative AI features for Interon products.
• Build LLM-powered applications using platforms such as OpenAI, Azure OpenAI, AWS Bedrock, Anthropic.
• Develop RAG solutions using enterprise documents and structured or unstructured data.
• Build AI agents and agentic workflows with tool calling, context management, and multi-step automation.
• Implement prompt engineering, structured outputs, grounding, guardrails, and response-quality controls.

Skills

Python programming

REST APIs

SQL

Git/GitHub

Problem solving

Communication

Education

Bachelor's or Master's in Computer Science/AI/Data Science/Software Engineering/IT

Tools

FastAPI

Node.js

React

TypeScript

Azure OpenAI

OpenAI APIs

AWS Bedrock

Job description

Job Title- Generative AI Engineer / GenAI Intern

Product Development | Interon IT Solutions

Location: Chantilly, Virginia Onsite

Experience: 1 5 years; internship and entry-level candidates considered

Employment: Full-time / Internship

Work Authorization: U.S. Citizen or Green Card holder

Department: Product Development / AI Engineering

About the Role

Interon IT Solutions is seeking a hands-on Generative AI Engineer or GenAI Intern to help build AI-powered enterprise and healthcare products. You will work with product and engineering teams to take practical AI use cases from concept and prototyping through development, testing, deployment, and continuous improvement.

The ideal candidate enjoys building real applications with LLMs, Retrieval-Augmented Generation (RAG), AI agents, APIs, and cloud technologies not simply experimenting with prompts or AI tools.

Key Responsibilities

• Design, develop, test, and enhance Generative AI features for Interon products.
• Build LLM-powered applications using platforms such as OpenAI, Azure OpenAI, AWS Bedrock, Anthropic, or similar services.
• Develop RAG solutions using enterprise documents and structured or unstructured data.
• Build AI agents and agentic workflows with tool calling, context management, and multi-step automation.
• Implement prompt engineering, structured outputs, grounding, guardrails, and response-quality controls.
• Design retrieval systems using embeddings, vector search, semantic search, and hybrid search.
• Develop backend APIs and microservices with Python, FastAPI, Node.js, or comparable frameworks.
• Integrate AI capabilities with enterprise applications, databases, APIs, and business workflows.
• Support AI-powered web applications using React, TypeScript, or modern frontend frameworks.
• Evaluate LLM applications for accuracy, relevance, hallucinations, latency, security, and cost.
• Implement testing, logging, monitoring, observability, and evaluation processes for GenAI applications.
• Deploy and operate AI applications using AWS and/or Azure services.
• Participate in Git-based development, code reviews, CI/CD, technical documentation, and collaboration with product owners and business teams.
• Research emerging GenAI technologies and recommend practical applications for Interon products.

Required Qualifications

• 1 5 years of experience in software development, AI/ML, data engineering, or a related technical field. For internship or entry-level candidates, academic projects, internships, hackathons, or independently developed applications may substitute for professional experience.
• Bachelor s or master s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, Information Technology, or a related field.
• Strong Python programming skills and working knowledge of REST APIs, JSON, databases, and backend development.
• Understanding of Generative AI, LLMs, embeddings, prompt engineering, RAG, and AI application design.
• Experience or project exposure with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar frameworks.
• Familiarity with SQL, relational databases, Git/GitHub, and modern software development practices.
• Strong analytical, problem-solving, communication, and collaboration skills.
• Ability to learn new AI technologies quickly and work onsite in Chantilly, Virginia.
• Must be a U.S. Citizen or U.S. Permanent Resident (Green Card holder).

Preferred Qualifications

• Azure AI Foundry or Azure OpenAI
• AWS Bedrock or OpenAI APIs
• Agentic AI, LangGraph, or multi-agent workflows
• RAG architecture, vector databases, PostgreSQL/pgvector, or Azure AI Search
• React, TypeScript, or FastAPI
• AWS Lambda, API Gateway, S3, RDS, or related cloud services
• Docker, GitHub Actions, CI/CD, AI evaluation, or observability
• Healthcare technology, HR technology, workflow automation, or enterprise SaaS

Potential Product Initiatives

The selected candidate may contribute to production-oriented solutions such as:

• AI-powered HR and recruiting solutions
• Candidate and resume matching
• Enterprise knowledge assistants and RAG applications
• AI agents for business workflow automation
• Healthcare workflow and administrative automation
• Document intelligence and information extraction
• Prior authorization and payer knowledge solutions
• AI-powered analytics and decision-support capabilities

What We Value

We value candidates who can demonstrate what they have built. A GitHub portfolio, working prototype, hackathon project, or independently developed application involving RAG, AI agents, LLM integrations, semantic search, workflow automation, API development, or cloud-based AI will be a strong advantage.