Join CACI's AI Enablement Team as a Generative AI Engineer delivering rapid, high-impact AI solutions in 1-2 month engagements. You'll build RAG pipelines, conversational AI, and multi-agent systems using our solution catalog, while helping program teams become self-sufficient through hands-on delivery and knowledge transfer.
Responsibilities
Build and deploy production-ready AI applications (RAG, conversational AI, multi-agent systems) across short program engagements.
Implement GenAI solutions using vector databases, LLM orchestration frameworks, and managed AI services with strong observability and security practices.
Integrate LLM APIs and services into existing workflows; apply responsible AI guardrails; troubleshoot cloud and on-prem integration issues.
Deliver workshops, documentation, and paired development to ensure teams can independently operate and extend AI systems.
Improve AI application templates and document emerging techniques based on field experience.
Validate program team readiness for independent AI operations.
Stay current with new GenAI tools and patterns and share insights with the team.
Requirements
5+ years software engineering experience with strong Python and JavaScript; ability to build and maintain production systems using modern development workflows and Git.
Hirevector is a professional services and recruitment firm that provides an AI-powered technical interview intelligence platform. The company focuses on standardizing the hiring process through conversational, AI-driven assessments to ensure fairness, reduce bias, and improve candidate evaluation.
Bachelor's degree in Computer Science or a related major.
Ability to obtain a U.S. Secret Clearance.
Practical experience developing LLM applications, including agentic patterns, RAG, context engineering, vector databases, and observability fundamentals; familiarity with evaluation-driven development and model routing.
Experience monitoring LLM performance, mitigating failure modes, and applying responsible AI practices (bias checks, guardrails, validation).
Strong API integration skills with REST and distributed systems.
Working experience with a major cloud provider (AWS/Azure/GCP), plus familiarity with Docker, CI/CD, IaC concepts, and core security practices.
Understanding of ML fundamentals relevant to LLM systems.
Ability to deliver quickly in unfamiliar environments and adapt to changing requirements.
Strong communication skills and experience creating clear technical documentation and explanations.
Pragmatic delivery mindset with sound architectural trade-off judgment.
Active user of AI tooling and continuous learner in GenAI.
Experience with agile workflows (GitLab, Jira).
Nice to Have
Experience building agentic systems with frameworks such as Agno, LangGraph, CrewAI, or OpenAI Agents; familiarity with LLM observability platforms and vector database technologies.
