GenAI Context Engineer

Job Title: GenAI Context Engineer
Duration : Permanent Full Time
Location : Strongsville, OH, Dallas, TX, or Pittsburgh, PA.
Work Mode : 5 Days Onsite

Looking to hire a Context Engineer who will be responsible for designing, building, and optimizing the enterprise knowledge and retrieval foundation that powers Generative AI applications. This role focuses on enabling high quality, grounded, and context aware AI experiences through Retrieval Augmented Generation (RAG), semantic search, metadata engineering, and enterprise knowledge orchestration.


The Context Engineer ensures AI systems retrieve the right information, from the right sources, at the right time — securely, accurately, and in alignment with enterprise governance standards.


Future duties and responsibilities

• Design and implement enterprise Retrieval Augmented Generation (RAG) architectures for GenAI platforms and applications.
• Build and optimize semantic retrieval pipelines, vector search implementations, and contextual grounding frameworks.
• Develop ingestion pipelines for enterprise knowledge sources including SharePoint, Confluence, Jira, APIs, databases, and document repositories.
• Define metadata, taxonomy, ontology, chunking, and embedding strategies to improve retrieval relevance and AI response quality.
• Implement permission aware retrieval and secure knowledge access aligned with enterprise governance and compliance requirements.
• Design and optimize hybrid search architectures combining vector search, keyword search, and knowledge graph capabilities.
• Collaborate with Value Engineers, architects, and business stakeholders to translate enterprise knowledge into scalable AI ready knowledge structures.
• Improve groundedness, citation accuracy, retrieval precision, and hallucination reduction across GenAI solutions.
• Maintain knowledge lineage, auditability, and contextual traceability for enterprise AI workflows.
• Support AI evaluation, observability, and continuous improvement initiatives for retrieval quality and search performance.
• Work closely with governance, security, and compliance teams to ensure responsible and secure enterprise AI knowledge access.
• Contribute to reusable enterprise knowledge engineering patterns and platform accelerators.

• 6+ years of experience in knowledge engineering, enterprise search, data engineering, AI engineering, or platform engineering roles.
• Experience building enterprise AI search or knowledge platforms in banking, financial services, healthcare, or other regulated industries.
• Familiarity with knowledge graphs, ontology modeling, AI observability, and enterprise governance frameworks.
• Understanding of responsible AI, groundedness evaluation, and enterprise compliance requirements for GenAI systems.
• Hands on experience with Retrieval Augmented Generation (RAG), semantic search, embeddings, vector databases, and enterprise knowledge systems.
• Strong programming skills in Python and experience with API based integrations.
• Experience with GenAI and retrieval technologies such as:
  o Azure OpenAI / OpenAI
  o Azure AI Search
  o LangChain / Semantic Kernel
  o Elasticsearch / OpenSearch
  o Vector databases and embedding frameworks
• Experience designing ingestion pipelines, metadata frameworks, chunking strategies, and contextual retrieval systems.
• Strong understanding of enterprise data governance, access control, lineage, and permission aware retrieval. Experience integrating enterprise content systems including SharePoint, Confluence, Jira, document repositories, and enterprise APIs.
• Familiarity with cloud platforms such as Azure, AWS, or GCP and containerized environments.
• Strong analytical, troubleshooting, and problem solving skills.
• Excellent communication and collaboration skills with the ability to work across engineering, architecture, governance, and business teams.

• LangChain
• LangGraph
• LlamaIndex
• Microsoft Azure AI Solution
• OpenAI
• Python
• Retrieval-Augmented Gen.(RAG)

Ref: #404-IT Pittsburgh