---
title: 'ML Engineer, Retrieval & Grounded Generation at DEFCON AI'
canonical: 'https://feeny.ai/job/ml-engineer-retrieval-grounded-generation-defcon-ai-united-states-0hc6tabj65br'
type: 'job'
last_seen: '2026-11-06'
---

# ML Engineer, Retrieval & Grounded Generation at DEFCON AI

- **Company:** DEFCON AI
- **Location:** United States
- **Work type:** remote
- **Posted:** 2026-10-01
- **Last confirmed live:** 2026-11-06
- **Apply:** https://job-boards.greenhouse.io/defcon/jobs/5253391007

## Job description

## ABOUT DEFCON AI

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. 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.

## About the Role

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.

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.

This is a fully remote role, with occasional travel to DEFCON AI HQ, customer sites, and vendor facilities as required.

## Key Responsibilities

- Implement embeddings, vector storage, and retrieval across a large, provenance-tracked evidence base
- Integrate language models so generated text is bound to cited source records; test for citation failures rather than assuming them away
- Design prompts and output schemas
- Own model packaging, versioning, serving, and rollback
- Instrument telemetry for retrieval and generation quality, recommendation/version attribution, overrides, abstentions, grounding failures, latency, throughput, and measurement events defined with Model Test
- Provide bounded model assistance for difficult narrative extraction where deterministic processing is insufficient, with every output tied to its source passage
- Supply the recorded rule context to every model-assisted step, so each output carries the exact rule versions and ordered context it received
- Maintain a modular in-boundary serving path, self-hosted or managed, alongside the primary managed inference service, so the platform does not depend on one provider’s availability or approval

Required Qualifications

- 5+ years of experience, including a production or near-production retrieval-augmented (RAG) system you built yourself
- Ability to speak in detail to your retrieval design, which vector store you used and why, how you tested grounding, what citation failures looked like in practice, and how rollback worked
- Strong Python, with hands-on experience in embeddings and vector retrieval at scale
- Clarity on what actually shipped in past work — prototype, proposal, or deployed code — since that distinction matters more here than the title on a resume
- US Citizenship Required
- Active US Secret clearance required to start.

## Preferred Qualifications

- Experience deploying models into restricted or air-gapped environments
- Self-hosted or open-weight model operation
- Fine-tuning, adapters, or custom embeddings
- Federal DevSecOps, RMF, ATO, or DoW cloud environment experience
- Active Top Secret clearance

What Success Looks Like

- Generated explanations that assert no more than the sources support, with the citation path intact and citation failures tested rather than assumed away
- A retrieval system that performs at scale on a large, provenance-tracked evidence base
- Model rollback that works when it's needed, with telemetry complete enough that measurement does not require manual reconstruction

## What We Offer

- A fully remote, results-based environment
- Competitive salary, bonus, and equity package
- 100% employer paid, comprehensive health insurance including medical, dental, and vision for you and your family
- Unlimited PTO, with your manager's approval
- Flexible work environment where you manage your work day
- 14 weeks of fully-paid parental leave

Salary Range: $165,000–$200,000. This represents the typical salary range for this position based on experience, skills, and other factors. We’re an Equal Opportunity Employer: You’ll receive consideration for employment without regard to race, sex, color, religion, sexual orientation, gender identity, national origin, protected veteran status, or on the basis of disability.

Applicant Data Disclosure

By submitting an application, you acknowledge that Defcon AI uses third-party service providers to facilitate its recruitment and hiring processes. These providers include applicant tracking systems, candidate verification platforms, and fraud detection tools (collectively, "Hiring Platforms"). Your application materials, including your résumé, cover letter, work samples, responses to application questions, and any other information you submit, may be transmitted to and processed by these Hiring Platforms for the following purposes:

- Managing and administering your application throughout the hiring process;
- Verifying the accuracy and authenticity of application materials, including by cross-referencing information you provide against publicly available sources and proprietary databases;
- Identifying indicators of potentially fraudulent, fabricated, or materially misleading application content, including but not limited to discrepancies between submitted materials and publicly available professional profiles, geographic anomalies, and fabricated work histories.

Applications that are flagged through this process as containing indicators of fraud or material misrepresentation may be declined from further consideration. If you have questions about the status of your application or the evaluation process, please contact recruiting@defconai.com.

Defcon AI requires its Hiring Platform providers to process your information solely for the purposes described above and in accordance with applicable law. Your information will be retained only for as long as necessary to fulfill these purposes and any applicable legal obligations, after which it will be deleted in accordance with Defcon AI's data retention policies.

For more information about how your data is used, please refer to our Privacy Policy and [Applicant Privacy Notice](https://nam09.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.redcellpartners.com%2Fapplicant-privacy-policy%2F&data=05%7C02%7Ckat.creamer%40redcellpartners.com%7Cc0f94f3daed94dc7503108de8b61955e%7Cf861de501a2a42359dbf28afd57d1d97%7C0%7C0%7C639101448841578570%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=WoPiBMZqQyPPK5N4E1sCagkbMY2S8P3aSRSoy7T4los%3D&reserved=0).

## About DEFCON AI

## Company Overview
- **One-liner**: DEFCON AI builds AI-powered decision-augmentation platforms that optimize complex operations under uncertainty for national security, manufacturing, logistics, and healthcare organizations.
- **Entity Type**: Private (Seed stage; raised $44M total funding)
- **Headquarters**: McLean, Virginia, United States
- **Founded**: 2022
- **Founders**: Yisroel Brumer (Co-Founder & CEO) and Grant Verstandig (Co-Founder & Executive Chairman)

## Core Business
- **Primary industries**: National Security/Defense, Manufacturing, Logistics & Transportation, Healthcare
- **Target customers**: B2B — primarily U.S. Department of Defense and other government agencies, as well as large commercial enterprises in manufacturing, logistics, and healthcare.
- **Mission or purpose**: To deliver decision-augmentation capabilities that help organizations anticipate disruption, evaluate alternatives in real time, and make confident decisions before disruptions cascade.

## Products & Services
- **ARTIV Air**: Cloud-native optimization platform for airlift planners to rapidly generate and evaluate multiple mission scenarios, balancing effectiveness, efficiency, and resiliency for routing mission-critical cargo and personnel.
- **R-ALIGN**: Enables logistics planners to model and evaluate global multimodal operations (air, sea, rail, road) using time-sensitive optimization in contested and dynamic environments.
- **FlightForge**: AI-driven tool that delivers mission-ready flight schedules in seconds, balancing key factors for accuracy and efficiency with real-time crew-to-sortie visibility.
- **DockForge**: Optimizes ship maintenance scheduling by assigning jobs across dry docks and shipyards, maximizing throughput and allowing planners to explore trade-offs.
- **R-IMS (Resilient Infrastructure Management System)**: Provides real-time view of capacity, dependencies, and schedule risk through simulation and scenario analysis for infrastructure and program teams.
- **HelioNet**: Helps enterprises design resilient, cost-efficient global logistics networks through advanced modeling and long-horizon optimization (warehouse/hub location, tariff/disruption scenarios).
- **SimSource**: Advanced optimization, simulation, and forecasting platform for managing complex, nested scheduling demands under uncertainty in manufacturing.
- **Synapse Scheduler**: Uses optimization, ML, and LLMs to generate workforce schedules that meet staffing needs and individual preferences (targeting healthcare).

## Market Standing
- **Valuation/Market Cap**: Not publicly disclosed.
- **Key Metric**: Total funding of **$44.0M** (Seed round led by Bessemer Venture Partners in August 2024; earlier venture round in October 2022).
- **Notable Investors/Partners**: Bessemer Venture Partners (lead), Red Cell Partners, and other undisclosed investors. The company was founded in response to a direct request from the U.S. Department of War.
- **Growth Signals**: Rapid transition from concept to mission-ready platform since founding in 2022; growing network of partners; expansion into commercial sectors (manufacturing, healthcare, logistics) beyond initial defense focus. LinkedIn shows 3,361 followers (+33.4% yearly).

## Competitive Advantages
- **Deep domain expertise**: The team combines senior defense leaders, algorithm developers, and operators, bridging theory and real-world execution.
- **Proven government pedigree**: Founded to meet a direct need from the Department of War, giving it strong credibility and an existing customer base in national security.
- **Cross-industry applicability**: Core optimization technology is platform-agnostic and has been adapted to manufacturing, healthcare, and logistics — not just defense.
- **Focus on uncertainty**: Unlike traditional static planning tools, the entire product suite is built to handle contested, dynamic, and uncertain environments.

## Strategic Focus
- **Current priorities**: Scaling the platform across multiple industries (defense, manufacturing, logistics, healthcare) and deepening capabilities in resilient optimization.
- **Direction for growth**: Expanding the partner network, continuing to win government contracts, and building out commercial applications for complex scheduling and supply chain resilience.

## Why Work Here
- **Culture highlights**: Mission-focused team of world-class AI engineers, data scientists, and mathematics experts working on pressing national challenges. Emphasis on collaboration, transparent communication, and operational impact.
- **Remote/hybrid/office policy**: **Remote-first** — ability to work fully remote within the United States. Certain roles may have in-office requirements.
- **Notable perks**: 100% employer-paid health insurance (medical, dental, vision) for employee and family; Unlimited PTO with management approval (all federal holidays observed); 14 weeks paid parental leave (maternity and paternity) at normal pay; 401K and FSA available; professional development and continued learning opportunities.
- **Engineering culture**: Building with bleeding-edge AI, mathematical optimization, and mission-grade software engineering. The team values rapid iteration and real-world deployment over theoretical work.

## Sources
1. [defconai.com](https://www.defconai.com/)
2. [defconai.com/careers](https://www.defconai.com/careers)
3. [defconai.com/about](https://www.defconai.com/about)
4. [boards.greenhouse.io/defcon](https://boards.greenhouse.io/defcon)
5. [linkedin.com/company/defcon-ai](https://www.linkedin.com/company/defcon-ai)

## Other roles at DEFCON AI

- [Controller](https://feeny.ai/job/controller-defcon-ai-mclean-3f2y567mv0qb) — Mclean, VA
- [IT Help Desk Specialist](https://feeny.ai/job/it-help-desk-specialist-defcon-ai-mclean-yc3pkxnmypjv) — Mclean, VA
- [Senior Entity Resolution Engineer](https://feeny.ai/job/senior-entity-resolution-engineer-defcon-ai-united-states-1vhe7q9xv1a3) — United States
- [Model Test and Measurement Engineer](https://feeny.ai/job/model-test-and-measurement-engineer-defcon-ai-united-states-2re9pe19frwr) — United States
- [Information Extraction Engineer](https://feeny.ai/job/information-extraction-engineer-defcon-ai-united-states-agn4q9kc11ka) — United States
- [Senior Data Platform Engineer](https://feeny.ai/job/senior-data-platform-engineer-defcon-ai-united-states-rjjmm1y0kf5r) — United States
- [Triad Modernization Advisor (1099)](https://feeny.ai/job/triad-modernization-advisor-1099-defcon-ai-offutt-afb-61ek5pfz3hts) — Offutt Afb, NE