Innovative Defense Technologies

Automated software testing and defense cybersecurity.

AI Implementation Engineer

AI Application EngineeringConfirmed live in the last 24 hours

Full-time$114k - $231k

About the Job

Requirements

A bachelor's degree in Information Technology, Computer Science, Computer Engineering, Electrical Engineering, Systems Engineering, Physics, or Mathematics, or equivalent full-time professional experience.
Five to ten or more years of professional experience in software engineering, machine learning engineering, AI engineering, or related technical roles.
Proficiency in Python, including experience with NumPy and Pandas.
Hands-on experience with production local inference engines such as vLLM, SGLang, Triton Inference Server, or TensorRT-LLM.
Experience building software with one or more modern AI/ML frameworks such as PyTorch, TensorFlow, LangChain, LangGraph, Semantic Kernel, or AutoGen.
Experience with Linux and hardening, including fapolicy, SELinux, or FIPS.
Experience with commercially available AI tooling or chat.
Experience hosting LLM servers and hosting different chat and embedding models.
Experience with distributed networking, including reverse proxies, load balancing, or firewalls.
Experience with containerization.
Ability to work independently on technical tasks while collaborating effectively in a team environment.
Ability to shift between projects in an agile work environment.
Strong leadership capabilities and skills.
Strong documentation skills.
Ability to travel up to 10% of the time, as needed.
Ability to obtain and maintain an active Secret U.S. Security Clearance.
Ability to work on-site at least three days per week at the Arlington, Virginia or Mount Laurel, New Jersey location.

Responsibilities

Design and implement end-to-end agentic AI systems for on-premises, air-gapped environments that support planning, reasoning, tool use, and multi-step execution; build modular, testable components that progress from prototype to operational capability.
Develop integrations across large language models, APIs, data sources, and Model Context Protocol interfaces so intelligent agents can interact with external systems, retrieve context, and take action safely and reliably.
Build and optimize Retrieval-Augmented Generation pipelines connecting models to live knowledge sources, structured data, and enterprise content to improve factual grounding, contextual relevance, and response quality.
Create conversational systems and intelligent agents with memory, contextual awareness, adaptive decision-making, and support for multi-turn user and system interactions.
Translate technical objectives into working pipelines, run experiments, evaluate agent behavior, and iterate on prompts, orchestration logic, retrieval quality, and system performance to improve reliability and usability.
Architect local infrastructure to size, configure, and optimize local CPU/GPU workloads, using quantization techniques to maximize throughput.
Orchestrate disconnected environments and design and maintain offline model update pipelines and local package mirrors.
Gather, document, and validate technical and functional requirements from project artifacts, stakeholders, and mission needs to ensure feasibility, completeness, and alignment with operational goals.
Work with engineers, technical leads, and mission stakeholders to integrate AI capabilities into broader software and system architectures; participate in technical reviews, design discussions, and delivery planning.
Contribute to testing, debugging, and performance optimization of AI-enabled applications, including edge cases involving context management, retrieval failures, tool execution, and orchestration logic.
Stay current on advances in large language models, agent frameworks, orchestration methods, and applied AI engineering practices, and apply that knowledge to practical system design and implementation.
Document architectures, workflows, assumptions, and implementation decisions so solutions are maintainable, explainable, and transferable across teams.

Desired Qualifications

A master's degree in Engineering or another technical field is highly desired.
Experience hosting LLM servers on local hardware.
Experience with various GPU architectures, with NVIDIA preferred.
Experience with AI gateways.
Experience with LLM servers and model optimization, including VRAM, layers, quantization, fasttensor, KV cache, and parallelization.
Experience with LLM tool calling.
Experience with Retrieval-Augmented Generation.
Experience with vector stores.
Experience with Model Context Protocol.
Experience with container orchestration.
Experience managing and directing personnel while maintaining cost and schedule targets.
Problem-solving skills and the ability to navigate ambiguous situations.

About The Role:

Innovative Defense Technologies (IDT), a leading defense technology company, is seeking an AI Implementation Engineer to be part of our Warfare Systems team and based out of our Arlington, VA or Mount Laurel, NJ location.

The AI Implementation Engineer will design and deliver engineering-focused AI solutions that move beyond demos into reliable, mission-relevant systems. This role is ideal for an engineer who has extensive experience with commercially available AI tooling/chat, hosting LLM servers and has demonstrated ability to build end-to-end capabilities including MCP integrations, RAG pipelines, tool-using agents, and production-grade AI workflows.

Clearance & Location Requirements:

All applicants must be able to obtain/maintain an active Secret U.S. Security Clearance.
This is an on-site position. Requiring at least 3 days in office, based out of our Arlington, VA location or Mt. Laurel, NJ location.

What You Will Do:

Design and Build AI Solutions for On-Prem systems in Air-Gapped environment: Design and implement end-to-end agentic AI systems that support planning, reasoning, tool use, and multi-step execution in real-world environments. Build modular, testable components that move from prototype to operational capability.
Integrate Models and Tools for On-Prem systems in Air-Gapped environment: Develop integrations across LLMs, APIs, data sources, and Model Context Protocol (MCP) interfaces to enable intelligent agents to interact with external systems, retrieve context, and take action safely and reliably.
Develop Retrieval Pipelines for On-Prem systems in Air-Gapped environment: Build and optimize Retrieval-Augmented Generation (RAG) pipelines that connect models to live knowledge sources, structured data, and enterprise content to improve factual grounding, contextual relevance, and response quality.
Engineer Conversational and Agentic Interfaces for On-Prem systems in Air-Gapped environment: Create conversational systems and intelligent agents with memory, contextual awareness, adaptive decision-making, and support for multi-turn user and system interactions.
Implement and Evaluate AI Workflows for On-Prem systems in Air-Gapped environment: Translate technical objectives into working pipelines, run experiments, evaluate agent behavior, and iterate on prompts, orchestration logic, retrieval quality, and system performance to improve reliability and usability.
Architect local infrastructure to size, config, and optimize local CPU/GPU workloads, utilizing quantization techniques to maximize throughput, etc.
Orchestrate disconnected environments, design and maintain offline model update pipelines, local package mirrors, etc.
Scope and Define Requirements: Gather, document, and validate technical and functional requirements from project artifacts, stakeholders, and mission needs to ensure feasibility, completeness, and alignment with operational goals.
Collaborate Across Teams: Work closely with engineers, technical leads, and mission stakeholders to integrate AI capabilities into broader software and system architectures. Participate in technical reviews, design discussions, and delivery planning.
Support Technical Quality: Contribute to testing, debugging, and performance optimization of AI-enabled applications, including edge cases involving context management, retrieval failures, tool execution, and orchestration logic.
Learn and Apply Emerging Practices: Stay current on advances in LLMs, agent frameworks, orchestration methods, and applied AI engineering practices, and bring that knowledge into practical system design and implementation.
Communicate Technical Work: Clearly document architectures, workflows, assumptions, and implementation decisions so that solutions are maintainable, explainable, and transferable across teams.

Who You Are (Required):

Bachelor’s Degree in Information Technology, Computer Science, Computer Engineering, Electrical Engineering, Systems Engineering, Physics, Math, or equivalent full-time professional experience; Master’s Degree in Engineering or other technical field highly desired
5-10+ years of professional experience in software engineering, machine learning engineering, AI engineering, or related technical roles
Proficiency in Python, including experience with core libraries such as NumPy and Pandas
Deep hands-on experience with production local inference engines such as vLLM, SGLang, Triton Inference Server, or TensorRT-LLM
Experience building software with one or more modern AI/ML frameworks such as PyTorch, TensorFlow, LangChain, LangGraph, Semantic Kernel, or AutoGen
Experience with Linux and hardening (fapolicy/selinux/fips/etc)
Experience with commercially available AI tooling/chat
Experience with hosting LLM servers
Experience with hosting different models (chat/embedding)
Experience with distributed networking (reverse proxy/load balancing/firewalls/etc)
Experience with containerization
Ability to work independently on technical tasks while collaborating effectively in a team environment
Ability to shift from one project to another in an agile work environment
Strong leadership capabilities and skills
Strong documentation skills
Ability to travel up to 10% of the time, as needed

What Makes You Stand Out:

Experience hosting LLM servers on local hardware
Experience with various GPU architectures (NVIDIA preferred)
Experience with AI Gateways
Experience with LLM servers and model optimization (VRAM/layers/quantization/fasttensor/kv-cache/parallel/etc)
Experience with LLM toolcalling
Experience with RAG
Experience with vector stores
Experience with ModelContextProtocol
Experience with container orchestration
Experience managing and directing personnel while maintaining cost and schedule targets
Problem-solving skills with the ability to navigate ambiguous situations

If you see yourself reflected in this role and are excited about the impact you could make, we encourage you to apply! If you know someone who may be a great fit, please feel free to share this opportunity with your network.

Pay Range*: $114,000 - $184,000 or $135,000 - $231,000

*Pursuant to New Jersey Senate Bill 2310 IDT is required to disclose the “pay scale” or “pay range” associated with a job posting. Notably, however, this amount may not be reflective of actual compensation that may be earned as pay is dependent on a candidate’s experience, skills, and education. The posted range does not include bonuses, commissions, tips, or other benefits. Click here for additional information about Senate Bill 2310. IDT is often looking to place multiple candidates at various levels. Therefore, more than one pay range has been included, commensurate with experience.

About the Company

Innovative Defense Technologies

Automated software testing and defense cybersecurity.

IDT automates software testing, data analysis, and cybersecurity for Department of Defense mission-critical systems, using its patented Automated Test and ReTest (ATRT) technology to support the full software testing lifecycle from component tests to system integration and results analysis. The product automates test execution, configuration assessment, and result reporting, offering repeatable tests, on-demand regression checks for cyber threats, and statistically rigorous analysis to cut time and manpower. Its differentiation comes from the ATRT patent and its ability to tailor automated testing across large, complex systems for defense needs. The company's goal is to help field new software capabilities faster and more affordably by reducing the time and cost spent on software testing.

Company size: 201-500
Company stage: Grant
Total funding: $1.6M
Headquarters: Arlington County, VA
Founded: 2006

Recently Posted Jobs

Explore more opportunities at Innovative Defense Technologies

See more jobs