AI Full-Stack Engineer
ampcusSouth Riding (VA)
About the role
We're Hiring: AI Full-Stack Engineer
Location: Chantilly, VA (Onsite)
Duration:
Full-TimeAre you the right candidate for this opportunity Make sure to read the full description below.
About the Role:
We're looking for an experienced AI Full-Stack Engineer with a passion for building next-generation intelligent applications. You'll work at the intersection of cloud-native development, modern AI technologies, and scalable backend systems — designing and deploying AI-enabled applications that integrate LLMs, RAG architectures, agentic AI, and vector-based knowledge retrieval. If you love turning cutting-edge AI into secure, high-performing enterprise solutions — this role is for you.
What You'll Do:
AI Full-Stack DevelopmentDesign, develop, and maintain scalable full-stack Generative AI and Agentic AI applications Build responsive UIs and integrate them with APIs, AI services, and enterprise systems Collaborate with architects, product owners, and engineering teams to translate business needs into technical solutionsAPI & Cloud-Native DevelopmentDesign and develop RESTful and/or GraphQL APIsBuild, deploy, and maintain applications on AWSImplement microservices architectures with containerization, orchestration, observability, and infrastructure automationAI-Enabled Applications Integrate AI-driven capabilities using modern AI frameworks and cloud services Build LLM-powered solutions for conversational experiences, intelligent automation, and knowledge discovery Design RAG architectures and optimize prompts, model interactions, and retrieval strategies Agentic AI & Intelligent Workflows Design autonomous agent-based workflows that orchestrate services and support decision-making Build AI agents that interact with APIs, databases, and enterprise systems Implement multi-step reasoning, planning, and workflow automation Vector Databases & Knowledge Retrieval Build semantic search and vector-based retrieval capabilities Work with vector databases and search platforms Develop pipelines for document ingestion, embedding generation, indexing, and semantic retrieval Model Context Protocol (MCP) DevelopmentDesign, develop, and deploy MCP servers and services for secure AI-to-enterprise integration Build reusable MCP-enabled connectors for contextual access to enterprise systemsAI-Assisted Development & DevOpsLeverage AI-powered development tools to boost engineering productivity Design and maintain CI/CD pipelines for automated build, testing, deployment, and monitoring Support infrastructure automation using IaC and cloud-native DevOps services
What We're Looking For:
Bachelor's degree in Computer Science, Engineering, IT, or related field 7+ years of full-stack software development experience, with 3+ years focused on Generative AI and/or Agentic AIHands-on experience building and deploying LLM-powered applications Demonstrated experience with RAG architectures and knowledge retrieval systems Experience with LangChain, LangGraph, Semantic Kernel, AutoGen, or similar AI frameworksExperience with vector databases and semantic search technologiesExperience developing AI agents and agent orchestration frameworksExperience designing MCP servers, connectors, or related AI integration frameworksExperience with AWS AI/ML services (Amazon Bedrock, SageMaker, Amazon Q Developer, etc.)Strong AWS cloud architecture, deployment, and operations experience Experience with Docker and Kubernetes Frontend experience with React, Angular, or Vue.jsBackend experience with Python, Node.js, Java, or comparable technologiesExperience with RESTful APIs, GraphQL, and microservices Experience with AI-assisted development tools (Claude Code, Codex, Cursor, Cline, GitHub Copilot, or similar)CI/CD pipeline and DevOps best practices experience Knowledge of prompt engineering, model evaluation, AI governance, and responsible AIExperience with observability, monitoring, and telemetry platforms
Bonus Points:
- Master's degree in CS, AI, Data Science, or related disciplineAWS, Azure, Kubernetes, or AI/ML certifications
- Experience building enterprise-scale AI applications in regulated or highly secure environments
- Familiarity with hybrid cloud and multi-cloud architectures
Why Join Us?
- Work on cutting-edge AI initiatives with real enterprise impact
- Collaborate with a talented, innovation-driven engineering team
- Grow your skills across the latest AI, cloud, and full-stack technologies
- Interested? xxoysbn Apply now or DM us for more details![Insert Application Link]#AIJobs #FullStackEngineer #GenerativeAI #AgenticAI #LLM #RAG #MCP #AWS #Kubernetes #Docker #LangChain #Vector
- Database #Machine
- Learning #Hiring #TechJobs #AIEngineer #CloudNative #DevOps #Prompt
- Engineering #NowHiring
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.