AI Engineer
ARCHIVED
We can't find an active application page for this role right now. It may reopen or be listed elsewhere. Use Next Steps to search for an active apply link and similar live jobs.
AI Engineer – Generative AI / LLMJob Overview Datgroup LLC is seeking an experienced AI Engineer to design, build, and deploy Generative AI solutions supporting mission-critical federal systems. This is a hands-on engineering role focused on developing production-ready applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), vector search, agentic workflows, and AWS-native AI services. You will work across the full GenAI application lifecycle, including data ingestion, chunking, embeddings, retrieval, prompt orchestration, model integration, evaluation, security, deployment, monitoring, and optimization. The ideal candidate combines strong Python and software engineering skills with practical experience building LLM-powered applications and understands how to take AI solutions from prototype through secure, scalable production deployment. Core Technology Stack: Python | LLMs | RAG | AWS Bedrock | Amazon OpenSearch | Vector Search | Embeddings | APIsResponsibilitiesDesign, build, and deploy LLM-powered applications and intelligent automation solutions for enterprise and mission-focused environments. Integrate Large Language Models into existing applications, workflows, APIs, and enterprise systems. Design and implement scalable Retrieval-Augmented Generation (RAG) architectures. Build end-to-end RAG pipelines covering ingestion, chunking, embedding, indexing, retrieval, reranking, grounding, and response generation. Develop and optimize chunking strategies, including semantic, recursive, token-based, and metadata-aware approaches. Create embedding pipelines for structured and unstructured enterprise data. Implement and optimize semantic and vector search solutions. Work with vector technologies such as Amazon OpenSearch, Pinecone, Weaviate, Chroma, FAISS, or similar platforms. Build and deploy GenAI solutions using AWS Bedrock and related AWS services. Integrate foundation models through APIs and modern application frameworks. Develop prompt orchestration and agentic workflows for multi-step AI-enabled processes. Integrate AI applications with enterprise APIs, microservices, databases, and existing application ecosystems. Develop rapid prototypes and transition successful concepts into secure, production-ready applications. Evaluate LLM responses, retrieval quality, grounding, contextual relevance, and overall system effectiveness. Implement techniques to reduce hallucinations and improve response accuracy and explainability. Develop and implement AI guardrails, security controls, access controls, and responsible AI practices. Optimize AI applications for performance, latency, scalability, reliability, and cost. Implement monitoring, logging, and observability for production GenAI applications. Support deployment using cloud-native technologies, containers, serverless architectures, and modern CI/CD practices. Troubleshoot model integration, retrieval, application performance, and production issues. Collaborate with engineers, architects, product teams, analysts, and customer stakeholders to translate requirements into working AI solutions. Participate in technical design sessions, demonstrations, implementation reviews, and customer-facing discussions. Contribute to AI architecture decisions, reusable engineering patterns, technical standards, and best practices. Stay current with emerging GenAI technologies, models, frameworks, and architectures and recommend appropriate solutions.
Required Qualifications:
U.S. Citizenship required and ability to obtain and maintain a Public Trust.
Bachelor's degree in Computer Science, Engineering, Data Science, or a related technical field.6+ years of relevant software engineering, AI/ML engineering, or related technical experience.
Strong proficiency in Python with experience developing production-grade applications.
Hands-on experience developing Generative AI / LLM-powered solutions.
Demonstrated experience integrating LLMs into enterprise applications or systems.
Hands-on experience designing and implementing RAG architectures.
Strong understanding of embeddings, semantic search, vector retrieval, and retrieval optimization.
Experience designing and implementing data chunking and indexing strategies.
Experience working with vector databases or vector-search technologies.
Experience developing and consuming REST APIs and integrating enterprise systems.
Understanding of scalable application and microservices architectures.
Experience working with AWS or comparable cloud environments.
Strong understanding of software engineering principles, testing, source control, and application development practices.
Ability to troubleshoot complex AI application, integration, retrieval, and performance issues.
Strong written and verbal communication skills.
Ability to collaborate directly with technical teams, business stakeholders, and customers.
Preferred Qualifications:
Active or previous DHS Public Trust.
Experience supporting technology solutions within DHS or another federal agency.
Hands-on experience with AWS Bedrock and the broader AWS AI/ML ecosystem.
Experience with Amazon OpenSearch, particularly vector search and semantic retrieval.
Experience working with foundation models such as Claude, Llama, Mistral, OpenAI models, or similar technologies.
Experience with GenAI frameworks such as LangChain, LlamaIndex, Haystack, or similar orchestration frameworks.
Experience developing agentic AI systems and multi-step AI workflows.
Experience with prompt engineering, model evaluation, RAG evaluation, and hallucination mitigation techniques.
Familiarity with model customization, fine-tuning, and model selection strategies.
Experience with MLOps/LLMOps, automated testing, CI/CD, and production AI deployment.
Experience with Docker, Kubernetes, serverless architectures, or other cloud-native deployment patterns.
Knowledge of AI security, data privacy, governance, and responsible AI practices.
Experience implementing authentication, authorization, logging, monitoring, and auditability for enterprise AI applications.
Experience working in Agile software development environments.
Federal consulting or customer-facing technical delivery experience is preferred.
Why Datgroup?
Datgroup LLC is a growing technology consulting company focused on helping federal customers solve complex technology, integration, data, cloud, and modernization challenges.
Our engineers work on meaningful technical problems supporting mission-critical government systems. We are focused on applying emerging technologies such as Generative AI to real operational challenges while maintaining the security, reliability, and engineering discipline required in federal environments.
At Datgroup, experienced engineers have the opportunity to contribute beyond individual development tasks. We value people who take ownership, solve difficult problems, communicate effectively, and contribute to technical decisions and engineering practices.
As we continue to grow, our engineers will have opportunities to help shape our technical capabilities, reusable solutions, engineering standards, and future direction.
Equal Employment Opportunity:
Datgroup LLC is an equal opportunity employer. Employment decisions are based on qualifications, merit, and business needs. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, disability, veteran status, genetic information, or any other status protected by applicable federal, state, or local law.