AI Engineer

Description

The Amivero Team Amivero’steam of ITprofessionalsdelivers digital services that elevate the federal government, whether national security or improved government services. Our human-centered, data-driven approach is focused ontruly understanding the environment and the challenge, and reimagining with our customer how outcomes can be achieved.

Our team of technologistsleveragemodern, agile methods to design and developequitable, accessible, and innovative data and software services thatimpacthundreds of millions of people.

As a member of the Amiveroteam you will use your empathy for a customer’s situation, your passion for service, your energy for solutioning, and your bias towards action to bring modernization tovery important, mission-critical, and public service government IT systems.

Special Requirements

• US Citizenship Required to obtain Public Trust
• Active DHS Clearance (preferred)
• Bachelor’s degree + 6 years of experience
• 3+ years of experience developing and optimizing solutions using Python or similar, with a strong focus on performance, scalability, and efficiency
• Extensive experience working with vector technology databases, designing and implementing solutions to efficiently store, search, and analyze high-dimensional data for real-time and large-scale applications
• GenAI and Bedrock experience

The Gist.

We are seeking a highly skilled Generative AI Engineer to design, develop, and deploy advanced AI-powered solutions leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and modern cloud-native architectures. This role will focus on integrating LLMs into enterprise systems, building scalable GenAI applications, optimizing data retrieval pipelines, and developing intelligent solutions using vector databases and AWS-native services such as Open Search and Bedrock.

The ideal candidate brings strong hands-on engineering expertise in Python, experience architecting and implementing RAG systems, deep understanding of data chunking and embeddings strategies, and practical knowledge deploying production-grade GenAI solutions.

• Design, build, and deploy LLM-powered applications and intelligent automation solutions for enterprise and mission-focused environments.
• Integrate Large Language Models (LLMs) into existing systems, workflows, products, and enterprise platforms using APIs, orchestration frameworks, and custom pipelines.
• Develop scalable Retrieval-Augmented Generation (RAG) architectures that improve response quality, accuracy, explainability, and contextual relevance.
• Engineer and optimize prompt orchestration, agentic workflows, and inference pipelines for production use.
• Develop prototypes and production-grade solutions leveraging open-source and commercial foundation models.
• Architect and implement robust RAG pipelines, including ingestion, indexing, retrieval, reranking, and response generation.
• Design and optimize data chunking strategies (semantic, recursive, token-based, metadata-aware chunking) to improve retrieval performance and model grounding.
• Create and manage embedding pipelines for structured and unstructured data sources.
• Implement and optimize vector search solutions using vector databases and similarity search technologies.
• Work with vector databases such as Open Search, Pinecone, Weaviate, Chroma, FAISS, or similar technologies for scalable retrieval systems.
• Develop data ingestion and knowledge management pipelines to support enterprise search and GenAI applications.
• Build and deploy GenAI solutions in cloud-native environments, with preference for AWS Bedrock, Amazon Open Search, and related AWS AI/ML services.
• Integrate LLM applications with enterprise APIs, microservices, databases, and existing application ecosystems.
• Support deployment of scalable and secure AI services using containers, serverless, and modern Dev Ops/MLOps practices.
• Optimize performance, latency, scalability, and observability of GenAI systems in production.
• Evaluate model performance, retrieval quality, hallucination reduction techniques, and system effectiveness.
• Implement guardrails, grounding strategies, and responsible AI controls for secure and…