Role overview
nou Systems, Inc. (nSI) is now officially a 100% ESOP company! We value teamwork and collaboration, and this transition allows us to take that commitment to a new level. nSI empowers our customers by supplying products, services, and expertise with powerful, data driven insights that transform defense systems and improve capabilities.
nou Systems, Inc. (nSI) is building systems that solve our nation's most challenging defense problems in an enjoyable, stimulating environment. We’re known for fielding revolutionary missile defense systems, pioneering step changes in RF seeker technology, introducing principled AI systems, and rapidly pioneering novel defense platforms, from space to the seabed. We're looking for talented builders with high levels of curiosity and extremely strong grounding in fundamentals and engineering first principles. If you're hungry for harder problems and want to build products that actually get into users’ hands, we’ve got you covered.
We are pleased to announce an opening for an AI Engineer who will join our Technical Solutions Division and JSTC2 Team in Huntsville, Alabama to build generative-AI-powered software that provides warfighting training exercise participants unparalleled access to information about the unfolding scenario. You’ll be part of a team that is not only modernizing the interface to the underlying warfighting simulations but also finding new and innovative ways of surfacing deep information about the scenario, providing end users the right information right when they need it.
What you'll work on
Our team is developing Government Off-the-Shelf software that has an existing customer base, is currently in use in ongoing warfighting exercises, and has a years-long product roadmap. We’re seeking an AI engineer who can help prototype new LLM-powered capabilities and integrate those capabilities into this software. You’ll be an integral part of a multidisciplinary software team combining a web-based front end, large-data-management back end, and on-prem LLM-powered data exploration.
We’re looking for an engineer who understands not only the under-the-hood details of LLMs but also how to use them in production code, and who strikes a balance between cutting-edge research and achievable, usable software at a fast tempo. We need people who enjoy working in tandem with other talented developers, architects, QA, and integration/DevOps, and who rise to the challenge of team communication and cohesion in an Agile/SAFe team. We want people who are passionate about the quality of software we deliver. You’ll need to be comfortable with developing capabilities that are delivered to end users on a 10-week cadence, helping elicit end user needs rather than being handed a pile of DOORS-managed requirements, and scoping work even in the absence of perfect information.
*Basic Qualifications:
Required Qualifications – lacking any disqualifies you from this job:**
- Bachelor’s degree in Machine Learning, Computer Science, Software Engineering, or related technical field, with a Master’s or higher preferred.
- 5+ years of professional experience in AI/ML engineering, with 2+ years focused on LLMs or similar generative models.
- Must possess or be able to obtain an active Secret Security Clearance.
- U.S. Citizen.
What we're looking for
- Experience with newer approaches to using LLMs as a natural language interface to a data store (not just traditional RAG).
- Experience with developing MCP tooling for custom applications.
- Comfortable developing in a containerized (Docker) Linux-based (Ubuntu) environment.
- Experience developing for a Continuous Integration/Continuous Development (CI/CD) pipeline.
- Active Top Secret clearance.