Back to jobs
Position:
We’re seeking a Senior AI Engineer with deep expertise in Retrieval-Augmented Generation (RAG) to design, build, and scale intelligent systems that power our document understanding, processing, and compliance automation platform. This is a hands-on, cross-functional role at the intersection of information retrieval, large language models, and production applications. The primary focus of this role will be to make customer data accessible and discoverable for grounding AI model responses, search, dynamic generation of data assets, and finding relationships within data.
Candidates must be U.S. citizens and are subject to a background check and unannounced drug testing. This is a hybrid role requiring periodic in-office collaboration for strategy and design sessions. We know how valuable your creativity and leadership skills are to our company’s success, and we offer an exceptional salary and benefits package commensurate with the responsibilities of the position.
AI Engineer - Retrieval-Augmented Generation (RAG)
Knoxville, Tennessee, United States
RegScale is a continuous controls monitoring (CCM) platform purpose-built to deliver fast and efficient GRC outcomes. We help organizations break out of the slow and expensive realities that plague legacy GRC tools by bridging security, risk, and compliance through controls lifecycle management. By leveraging CCM, organizations experience massive process improvements like 90% faster certification times, and 60% less audit prep time. Today’s expansive security and compliance requirements can only be met with a modern, CCM based approach, and RegScale is the leader in that space.
Position:
We’re seeking a Senior AI Engineer with deep expertise in Retrieval-Augmented Generation (RAG) to design, build, and scale intelligent systems that power our document understanding, processing, and compliance automation platform. This is a hands-on, cross-functional role at the intersection of information retrieval, large language models, and production applications. The primary focus of this role will be to make customer data accessible and discoverable for grounding AI model responses, search, dynamic generation of data assets, and finding relationships within data.
Candidates must be U.S. citizens and are subject to a background check and unannounced drug testing. This is a hybrid role requiring periodic in-office collaboration for strategy and design sessions. We know how valuable your creativity and leadership skills are to our company’s success, and we offer an exceptional salary and benefits package commensurate with the responsibilities of the position.
What You'll Do
-
Architect, prototype, and deploy RAG pipelines, combining vector search, hybrid retrieval, reranking, and contextual compression techniques.
-
Contribute to design and orchestration of multi-agent LLM systems using both community-frameworks and custom orchestration layers.
-
Build and integrate vector search systems (e.g., Milvus, pgvector, FAISS, Weaviate, Pinecone) for high-recall retrieval across structured and unstructured data.
-
Develop intelligent document preprocessing, chunking, and metadata enrichment strategies to enhance context relevance in retrieval.
-
Evaluate end-to-end system performance using both classical IR metrics (recall, precision) and LLM-specific evaluations (factuality, coherence, task success).
-
Design strategies to optimize RAG architectures for resource-constrained environments, balancing performance, latency, and cost-effectiveness.
-
Contribute to API-driven robust, observable, and secure AI infrastructure integrated into enterprise environments and services.
-
Collaborate closely with product managers, backend engineers, domain experts, and stakeholders to translate product goals into scalable AI solutions.
Key Qualifications
-
MS with 4 years of work experience or PhD with 2 years of post-graduate work experience, with a focus on information retrieval, NLP, ML, and LLMs.
-
Deep understanding of RAG architectures, including embedding generation, indexing strategies, reranking, and generation model integration.
-
Proficiency with vector databases and search libraries: pgvector, FAISS, Milvus, Pinecone, OpenSearch, etc.
-
Strong command of embedding models (OpenAI, Cohere, Sentence Transformers) and retrieval orchestration frameworks.
-
Experience with Pytorch, Transformers, REST APIs (Django, FastAPI, or Flask), and SQL.
-
Solid knowledge of classical IR and hybrid retrieval methods.
-
Deep expertise in search relevance, ranking, and retrieval systems, including vector search and multimodal data handling.
-
Proven experience deploying information retrieval systems, ML models, LLMs, or RAG systems in production environments, with attention to latency, cost, and security.
-
Familiarity with tools for observability, evaluation, and model performance monitoring.
Nice to Have
-
Experience in enterprise AI applications with strict compliance, audit, or legal requirements.
-
Background in multi-modal search, or semantic search.
-
Contributions to open-source RAG or IR frameworks.
-
Published internal or external technical documents or research.
Apply for this job
*
indicates a required field