<div class="content-intro"><p>ABOUT DEFCON AI</p> <p>RESILIENCE IN THE FACE OF DISRUPTION. DEFCON AI is an insights company that leverages artificial intelligence, mathematical optimization, data analytics, and software engineering for resilient optimization of complex systems.<br>In today’s dynamically changing world, DEFCON AI’s technology aligns outcomes with operational goals, better decision making, and empowers customers to anticipate assess, and mitigate the impacts of disruptions.</p></div><p><span style="text-decoration: underline;"><strong>About the Role</strong></span></p> <p><span data-contrast="auto">This role sits in one of the most critical parts of the platform: determining when records from dozens of disparate sources represent the same real-world entity. Graph design and matching strategy are developed in-house, and <span style="text-decoration: underline;"><strong>you’ll be the engineer who turns those concepts into production-ready capability.</strong></span> You’ll shape implementation details, but this is first and foremost a builder role.</span><span data-ccp-props="{}"> </span></p> <p><span data-contrast="auto">You’ll join a team building technology that supports real-world government mission needs. The platform ingests and analyzes data from a wide range of sources, applies AI-assisted workflows to surface what matters most, and provides transparent, explainable recommendations that analysts can trust. Every match, merge, and relationship you create helps turn fragmented information into insight.</span><span data-ccp-props="{}"> </span></p> <p><span data-contrast="auto">You’ll own the matching build lifecycle end to end: blocking strategies, candidate generation, pairwise scoring, clustering, threshold policy, and the deduplication and known-entity checks that reuse the same engine. You’ll also build the provenance framework that lets every node, edge, and assertion in the graph be traced to the source that asserted it, so matching decisions are auditable and explainable.</span><span data-ccp-props="{}"> </span></p> <p><span data-contrast="auto">This is a fully remote role with occasional travel to DEFCON AI headquarters, customer sites, and partner facilities as needed.</span></p> <p><span data-ccp-props="{}"> </span></p> <p><span style="text-decoration: underline;"><strong><span data-contrast="none"><span data-ccp-parastyle="heading 2">Key Responsibilities</span></span></strong><span data-ccp-props="{"335559738":260,"335559739":120}"> </span></span></p> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{"335551671":0,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="0" data-aria-level="1"><span data-contrast="auto">Implement and refine entity-level record matching: blocking, candidate generation, pairwise scoring, clustering, and threshold policy</span><span data-ccp-props="{}"> </span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{"335551671":0,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="auto">Reuse one matching engine for record linkage, deduplication, and known-entity checks</span><span data-ccp-props="{}"> </span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{"335551671":0,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="auto">Establish provenance so every node and edge traces back to the source that asserted it</span><span data-ccp-props="{}"> </span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{"335551671":0,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="auto">Own the false-merge versus false-split tradeoff in matching decisions and make it explainable</span><span data-ccp-props="{}"> </span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{"335551671":0,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="auto">Own technical execution of the matching approach against the in-house design: the fixed reference dataset, candidate retrieval and final matching evaluated separately, and threshold recommendations with evidence for review</span><span data-ccp-props="{}"> </span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{"335551671":0,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="auto">Document matching logic in enough detail to se