AI Software Engineer

Second Front Systems; Washington (District of Columbia); Hybrid; USD 150,000 - 160,000; Full time

Benefits offered by this job

100% employer-paid medical, dental, &/

Job summary

Second Front Systems is seeking an AI Software Engineer to design and ship agentic AI systems, spanning LangGraph and LangChain tooling, multi-step orchestration, and cloud infra. You’ll craft scalable ingestion, embedding, retrieval, and tool suites, and ensure governance and measurable output quality across production pipelines.

Join a mission-driven team delivering AI workflows in onboarding, deployment, monitoring, and remediation, with a focus on reliability and cross-functional

Qualifications

• 2+ years of production software/ML/AI engineering shipping LLM-based systems.
• Experience building agentic AI systems with multi-step orchestration.
• Experience with Retrieval-Augmented Generation and vector stores.
• Deploy containerized AI services to cloud using Docker/Kubernetes and infra as code.
• Ability to communicate AI concepts to non-technical stakeholders.
• U.S. citizenship and residence in approved hiring hubs.

Responsibilities

• Architect production agentic AI systems with LangGraph and LangChain focusing on reliability and measurable output quality.
• Build agent components including ingestion pipelines, embeddings, chunking, retrieval, and tool suites.
• Connect agents to corporate tools via Model Context Protocol and MCP servers/clients.
• Operate cloud infrastructure for R&D AI systems (EKS, Terraform, Helm) and CI patterns.
• Measure output quality via evaluation suites and contribute to model selection decisions.
• Collaborate with Product teams to scope AI opportunities and governance standards.

Skills

LangGraph

LangChain

Tool-calling

Kubernetes (EKS)

Terraform

Cloud deployment

Stakeholder comms

Tools

Docker

AWS Bedrock

OpenAI

Self-hosted models

GitOps

Job description

AI Software Engineer

Second Front Systems is looking for an ambitious, mission-focused, full-stack AI Software Engineer to strengthen our growing Research and Development organization building AI-native platform capabilities.

Operating at the intersection of AI systems engineering and national security infrastructure, you will be responsible for designing, building, and shipping production agentic AI systems while establishing the cloud infrastructure and governance they operate within.

You will move from prototype to production across agent design, implementation, LLM integration, and cloud deployment, ensuring measurable output quality and user authorization at every stage, ensuring that Game Warden and downstream products integrate AI as foundational capability rather than feature.

Your solutions will include evaluative rigor and organizational fluency.

We need someone capable of building and shipping agentic systems with LangGraph, LangChain, tool-calling, and multi-step orchestration; operating cloud infrastructure (EKS, Terraform, Helm) and LLM gateway patterns across AWS Bedrock, Anthropic, OpenAI, Cohere, self-hosted models and provider-agnostic architectures; and defining and measuring agent quality through evaluation suites, then translating results into model selection and architecture decisions.

As a key partner to our Product and Engineering teams, which are seeking to identify and deploy AI workflows across onboarding, deployment, monitoring, and remediation, you will advise on agent architecture and scope, model selection, implementation, and responsible AI governance.

You will build documentation and reusable components that multiply organizational AI capability, serving as technical authority translating research-grade AI systems into mission-ready product.

Note:

Candidates must reside in one of our approved hiring hubs:

• DC/Maryland/Virginia
• Raleigh/Durham/Chapel Hill, NC
• Denver/Colorado Springs, CO
• Dallas/Fort Worth, TX

This is a full-time position.

What You'll Do

• Architect production agentic AI systems using LangGraph and LangChain with focus on reliability, traceability, and measurable output quality.
• Build agent components including ingestion pipelines, embedding strategies, chunking, retrieval, and re-ranking, and tool suites across managed knowledge-base services, vector databases, and internal and external APIs.
• Connect agents to corporate tools and knowledge through Model Context Protocol, constructing both MCP servers and consuming clients.
• Establish and operate cloud infrastructure for R&D AI systems: Amazon EKS, Terraform, Helm, and GitOps delivery patterns.
• Measure agent and LLM output quality through evaluation and regression suites covering groundedness, faithfulness, relevance, and retrieval quality, running in CI.
• Partner with Product teams to scope high-leverage AI opportunities across workflows and advise on agent design, model selection and output quality standards.

What You Bring

• 2+ years full-time software, ML, or AI engineering experience with hands-on production work building and shipping LLM-based systems.
• Hands-on experience building agentic AI systems with tool-calling agents and multi-step orchestration using LangGraph, LangChain, or equivalent.
• Production experience with Retrieval-Augmented Generation including vector stores, embedding models, chunking strategies, and retrieval quality optimization.
• Experience deploying containerized AI services to cloud environments using Docker, Kubernetes (EKS preferred), and infrastructure as code (Terraform preferred).
• Demonstrated ability to communicate AI concepts and recommendations to non-technical stakeholders and cross-functional teams.
• U.S. citizenship and residence in approved hiring hub: DC/Maryland/Virginia, Raleigh/Durham/Chapel Hill NC, Denver/Colorado Springs CO, or Dallas/Fort Worth TX.

Preferred

• Experience building MCP servers or clients, or integrating agents with enterprise tools and knowledge bases.
• Experience with AWS AI services such as Bedrock Knowledge Bases, AgentCore, and OpenSearch.
• Experience operating LLM gateways or serving infrastructure (e.g., LiteLLM, vLLM, GPU-backed self-hosted models), including single- and multi-tenant designs.
• Experience driving AI adoption across a product organization: not just building, but enabling others to use AI effectively.
• Experience working in or with the Department of Defense, federal agencies, or regulated environments, and familiarity with compliance frameworks such as NIST 800-53, FedRAMP, or NATO D32.

The base salary for this position will fall between $150,000 and $160,000. Your ultimate compensation will be determined by professional background, technical proficiency, seniority, and regional cost factors. Furthermore, this opportunity includes potential eligibility for equity awards and discretionary bonuses, rounding out a comprehensive total rewards offering.

Success at 2F Looks Like

• A proactive and solutions oriented mindset
• Viewing obstacles as opportunities for growth
• Having a bias toward action and tangible, measurable results
• Being team-oriented with a focus on personal responsibility and autonomy

Perks & Benefits

• This role is a full time position.
• As a public benefit corporation, we’re a team of purpose-driven trailblazers transforming the future of U.S. national security.
• We hire the best to do their best and, as such, we are committed to providing the perks and benefits you need to be successful—both in- and outside the workplace.
• Competitive salary
• 100% employer-paid medical, dental, and vision coverage for you and your dependents
• 401(k) with a 3% company contribution
• Comprehensive wellness benefits, including a One Medical membership, mental health resources, family planning support, and more
• Equity incentive plan
• New hire technology and home office stipend
• Annual professional development stipend
• Flexible paid time off, plus all federal holidays
• Generous parental leave
• Flexible remote work opportunities
• Employee referral bonus program

Who We Are

Second Front Systems (2F) is a public-benefit software company powering software for the free world. We eliminate the friction that slows innovation, enabling faster, more secure development and deployment of software across government and regulated networks. Built by national security veterans and backed by top-tier venture capital, our platform is trusted by the world’s leading organizations to cut deployment timelines from years to weeks. We move fast, solve hard problems, and deliver trusted capabilities where they’re needed most. Our work strengthens global security and gives the United States and its allies a lasting competitive advantage. Learn more at secondfront.com.

We are an equal opportunity employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity or expression, pregnancy, age, national origin, disability status, genetic information, protected veteran status, or any other characteristic protected by law.

State notices

• Colorado: In accordance with Colorado law, applicants may redact their date of birth, dates of attendance, and dates of graduation from any uploaded documents.
• Maryland: Under Maryland law, an employer may not require or demand, as a condition of employment, prospective employment, or continued employment, that an individual submit to or take a polygraph examination or similar test. An employer who violates this law is guilty of a misdemeanor and subject to a fine not exceeding $100.