AI Software Engineer

ArcheSys is a technology consulting firm delivering innovative cloud, AI, DevSecOps, and digital modernization solutions to Federal, State, and Commercial customers. We help organizations accelerate mission outcomes through cloud-native engineering, intelligent automation, and secure software development. We're seeking a AI Software Engineer who is passionate about building production-grade AI applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI. This is a hands-on engineering role where you'll design, develop, deploy, and optimize secure AI solutions running on AWS. This is a fully remote, full-time position offering the opportunity to work on emerging AI technologies that support mission-critical public sector initiatives. Location: This is a remote position. Residency Requirement: Candidates MUST have lived in the U.S. for at least 3 of the past 5 years and be authorized to work in the U.S. (Citizen, Permanent Resident, or EAD). Sponsorship: This position does not offer any type of sponsorship. Candidates must already be authorized to work in the U.S. (e.g., Citizen, Permanent Resident, or EAD). Clearance: Public Trust Clearance (or ability to obtain) Key Responsibilities AI Application Development • Design, develop, and maintain AI-powered applications using Python. • Build intelligent applications leveraging OpenAI APIs, Amazon Bedrock, and other enterprise LLM platforms. • Design and implement Retrieval-Augmented Generation (RAG) architectures using enterprise knowledge sources and vector databases. • Develop Agentic AI workflows capable of autonomous reasoning, planning, and task execution. • Build reusable AI services, APIs, and software components for enterprise applications. • Optimize prompts, model interactions, and application performance for reliability, scalability, and cost efficiency. • Leverage AI development tools safely and effectively, taking ultimate human accountability for the design, security, and test coverage of all generated code. Cloud & Infrastructure Engineering • Design, deploy, and maintain AI solutions on AWS. • Build Infrastructure as Code (IaC) using Terraform. • Develop containerized applications using Docker. • Deploy and manage workloads on Kubernetes. • Collaborate with DevOps engineers to automate deployments through CI/CD pipelines. • Ensure AI solutions meet security, scalability, and operational requirements. ‍ Software Engineering & Integration • Develop secure REST APIs and backend services. • Integrate AI capabilities with enterprise applications, cloud services, and external APIs. • Write clean, maintainable, well-tested, and reusable code following software engineering best practices. • Participate in architecture reviews, code reviews, and technical design discussions. Innovation & Research • Evaluate emerging AI frameworks, tools, and technologies. • Prototype new AI capabilities and rapidly validate proof-of-concepts. • Recommend improvements that increase developer productivity and enhance customer outcomes. • Help establish reusable AI patterns, templates, and best practices across projects. Documentation & Collaboration • Create technical documentation, architecture diagrams, implementation guides, and operational runbooks. • Work closely with Solution Architects, Cloud Engineers, Product Managers, and customers to translate business requirements into AI solutions. • Participate in Agile ceremonies, sprint planning, backlog refinement, and knowledge-sharing sessions. Required Qualifications Education & Experience • Bachelor's degree in Computer Science, Software Engineering, Information Technology, or related discipline (or equivalent professional experience). • 4–8 years of professional software engineering experience. • 2+ years of professional Python development experience. • Must be a U.S Citizen or Green Card Holder. Technical Skills • Strong Python programming skills. • Efficient prompt engineering • Experience building applications on AWS. • Experience integrating OpenAI APIs and/or Amazon Bedrock. • Hands-on experience implementing Retrieval-Augmented Generation (RAG) solutions. • Experience designing or developing Agentic AI workflows. • Experience developing RESTful APIs. • Experience using Terraform for Infrastructure as Code. • Experience with Docker and Kubernetes. • Experience using Git and modern CI/CD pipelines. • Strong understanding of software design principles, API development, and cloud-native architectures. Preferred Qualifications • Nice to have worked with LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar AI orchestration frameworks. • Nice to have worked with vector databases such as Pinecone, Amazon OpenSearch, pgvector, or Weaviate. • Experience with Amazon ECS, Amazon EKS, Lambda, API Gateway, DynamoDB, or S3. • Familiarity with prompt engineering, AI evaluation, and model observability. • Experience with DevSecOps and secure software de