<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><strong><span data-contrast="none"><span data-ccp-parastyle="heading 2">About the Role</span></span></strong><span data-ccp-props="{"335559738":260,"335559739":120}"> </span></p> <p><span data-contrast="auto">You'll join the analytics and AI engineering team behind a system that genuinely matters: an AI-assisted platform that pulls together records from dozens of external feeds, resolves them to the right person, surfaces what a human reviewer should look at first, and explains every recommendation in plain, defensible terms — running inside a secure government cloud environment. It's the kind of problem where the details you get right are the ones that count, which is exactly what makes it worth doing well.</span><span data-ccp-props="{"335559739":160}"> </span></p> <p><span data-contrast="auto">As ML Engineer, Retrieval & Grounded Generation, you'll build embeddings, vector storage, and retrieval at scale, and integrate language models so that every piece of generated text is bound to cited source records and citation failures are tested for rather than assumed away. You'll also own prompt and output-schema design; model packaging, versioning, serving, and rollback; and the telemetry hooks that make later measurement possible without manual reconstruction - real infrastructure for a real production system, not a demo.</span><span data-ccp-props="{"335559739":160}"> </span></p> <p><span data-contrast="auto">This is a fully remote role, with occasional travel to DEFCON AI HQ, customer sites, and vendor facilities as required.</span><span data-ccp-props="{"335559739":160}"> </span></p> <p><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></p> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="auto">Implement embeddings, vector storage, and retrieval across a large, provenance-tracked evidence base</span><span data-ccp-props="{"335559739":100}"> </span></li> </ul> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="auto">Integrate language models so generated text is bound to cited source records; test for citation failures rather than assuming them away</span><span data-ccp-props="{"335559739":100}"> </span></li> </ul> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="auto">Design prompts and output schemas</span><span data-ccp-props="{"335559739":100}"> </span></li> </ul> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="auto">Own model packaging, versioning, serving, and rollback</span><span data-ccp-props="{"335559739":100}"> </span></li> </ul> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="auto">Instrument telemetry for retrieval and generation quality, recommendation/version attribution, overrides, abstentions, grounding failures, latency, throughput, and measurement events defined with Model Test</span><span data-ccp-props="{"335559739":100}"> </span></li> </ul> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="6" data-aria-level="1"><span data-contrast="auto">Provide bounded model assistance for difficult narrative extraction where deterministic processing is insufficient, with every output tied to its source passage</span><span data-ccp-props="{"335559739":100}"> </span></li> </ul> <ul> <li data-leveltext="●" data-font="" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769242":[8226],"469777803":"left","469777804":"●","469777815":"hybridMultilevel"}" data-aria-posinset="7" data-aria-level="1"><span data-c