Senior AI and Knowledge Systems Engineer

What You’ll Do

Enterprise Knowledge Platform: Design and build a knowledge system that brings together staff reports, plans, and tracked items that today live in separate places across Jira, Confluence, and SharePoint. 

Question Answering: Build NLP and LLM-based workflows that let a user ask a plain question, such as “give me a completed trip report” or “show me the burndown from our last trip,” and get an answer written the way the staff would write it. 

Staff Validation: Put staff in the loop to review outputs against how they would have answered, and use their feedback to tune the system until they trust it. 

Controlled Information Testing: Release only selected information to the model and observe what it surfaces, so we can measure accuracy, find gaps, and understand how the system behaves. 

User Testing: Watch users do the task the way they normally would, then test the system’s output against their results and use the differences to guide the next round of work. 

Prompt Engineering and Integration: Build and refine prompts, APIs, and MCP connections that link the model to Jira, Confluence, SharePoint, and the other data sources staff already use. 

Access Control and Need-to-Know: Make sure the system never shows a user anything they aren’t cleared or authorized to see. Answers must respect the permissions already set in Jira, Confluence, and SharePoint, along with classification markings, compartments, and need-to-know. This applies to every part of the system, including search indexes, embeddings, prompts, and model outputs. You will also build in audit logging and keep the data on the networks where it belongs. 

Working With Real-World Systems: Work with the systems as they are, not as the documentation says they should be. Some installations are not on current versions, APIs may be limited or unreliable, and MCP connectors may not exist for what you need. You will find workable paths, such as building your own connectors, adapting to older APIs, or pulling content another way, and document what you learn. 

Path to Enterprise Capability: Grow the first working version into an enterprise knowledge store, working toward initial and then full operational capability. 

Who We’re Looking For

• A builder who enjoys turning messy, siloed information into something people actually use
• Someone who learns new tools quickly and wants to work at the frontier of AI 
• Someone who stays productive when the tools are older, the APIs are inconsistent, or the connector they need hasn’t been built yet 
• Someone who spends time with end users and designs around how they really work 
• A self-thinker who is comfortable owning ambiguous problems and moving them forward 
• Someone who treats access control and data protection as part of the design from day one, not something added at the end 
• Someone who takes a human-in-the-loop approach and understands both the strengths and the limits of AI 
• Someone who cares about accuracy and can show how they know an answer is right 
• A clear communicator who can explain technical choices to engineers and to senior non-technical leaders
• A self-motivated individual who works well on their own and as part of a team 

Required Qualifications:   

• Active TS/SCI clearance with CI poly required to start
• Experience building NLP or LLM-based applications, including prompt engineering and working with LLM APIs 
• Experience designing and building APIs and integrating multiple data sources 
• Experience implementing access controls in data or search systems, such as role- or attribute-based access, permission-aware retrieval, and audit logging 
• Experience organizing large collections of documents or data so they can be searched and reused 
• Ability to explain technical work to non-technical users and leadership 

Desired Qualifications:  

• Experience with retrieval-augmented generation (RAG) and vector or graph-based search 
• Experience with one or more of Jira, Confluence, or SharePoint, including their APIs and how content is structured in them 
• Experience with MCP servers or similar tool-integration approaches for LLMs 
• Experience building custom MCP servers or connectors where no off-the-shelf option exists 
• Experience integrating with older or on-premises software versions and working around limited, inconsistent, or poorly documented APIs 
• Experience with knowledge management, knowledge graphs, or semantic data standards 
• Experience designing ways to test LLM output, including accuracy checks and human review 
• Experience building and deploying tools on JWICS or higher-classification networks 
• Familiarity with IC data handling, including classification markings, compartments, and need-to-know controls 
• Familiarity with how military or command staffs produce reports, plans, and operational products 
• Strong Python skills and experience with modern data and AI tooling 
• Experience working in Agile environments with short, iterative delivery cycles 
• Experience running user research or user testing on analytic or data-driven tools 

• The expected salary range within the Washington, DC metropolitan area is: $150,000 - 210,000. Final compensation is unique to each individual and will be determined based on factors such as experience, education, geographic location, and contractual requirements. This is not a guarantee.
• Benefits include Health/Dental/Vision, 401(k), Paid Time Off, STD/LTD/Life Insurance/Voluntary Life Insurance, Stipends, Referral Bonuses, and more.

BCore is proud to be an equal opportunity workplace. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, sexual orientation or any other characteristic protected by law.