AI Systems Engineer

Who we are:

Tria Federal delivers digital services and technology solutions that support the health and safety of veterans, service members and civilians. For two decades, federal agencies have relied on Tria companies to advance their critical missions and modernize their systems, so that they can uphold their commitment to the American people. Today, we are pushing the boundaries of possibility through partnerships and investments in artificial intelligence and emerging technologies, developing solutions for the biggest challenges that government will face tomorrow.

We are proud to employ and support military veterans who bring mission-first mindset, technical expertise, and leadership qualities that strengthen our work. Veterans, transitioning service members, and military spouses are strongly encouraged to apply.

Job Description:

We are looking for a highly skilled AI Systems Engineer who will be part of a collaborative and agile team that supports and builds modern, usable, and responsive applications for mission-critical U.S. federal government health IT solutions.The Senior AI Systems Engineer will operate in a fast paced innovation environment, rapidly developing and validating proof of concepts for advanced AI and machine learning use cases. The role centers on experimenting with cutting edge analytics tools, integrating them into a cloud based analytics ecosystem, and helping move successful concepts toward operational deployment. Responsibilities include hands on data exploration, prototyping, workflow automation, and contributing to secure, well governed MLOps practices. The Software Engineer will work closely with engineering and product teams to evaluate emerging tools, build technical demonstrations, document integrations, and communicate platform updates in a highly collaborative setting. data platform fluency, and agility to support cross-functional teams.

Mandatory Requirements:
* 5+ years of relevant software / systems engineering experience
* Software engineering background with deep experience building production grade applications and services.
* Expertise developing agentic AI systems, including planning, tool use, multi step reasoning, workflow execution, or autonomous decisioning logic.
* Hands on experience designing and implementing MCP based integrations, tool interfaces, or model driven service frameworks.
* Ability to translate ambiguous business or mission requirements into scalable AI-driven solutions, balancing technical feasibility with real-world impact.
* Proficiency with LLM development practices including fine tuning, RAG integration, prompt engineering, and interaction models for agent workflows.
* Strong Python development skills and familiarity with distributed compute environments, APIs, microservices, and cloud native architectures.
* Experience integrating agents or LLM driven components into cloud platforms (Azure, AWS, GCP) or large scale data ecosystems.
* Understanding of LLMOps/MLOps principles including versioning, testing, deployment automation, monitoring, and governance for agentic systems.
* Demonstrated ability to lead solution design, mentor developers, and communicate complex AI architectures to technical and non technical stakeholders.
* Experience with version control and modern CI/CD practices (e.g., Git/GitHub), including automated testing, deployment pipelines, and release management for production systems.
* Ability to obtain/maintain a Public Trust clearance.

Preferred Requirements:
* Experience building or contributing to multi agent systems or coordinated agent workflows.
* Familiarity with frameworks such as LangChain, LlamaIndex, Strands Agents, LangGraph, CrewAI.
* Knowledge of evaluating agent performance, implementing guardrails, or designing safe action execution patterns.
* Hands on work with vector databases, embedding models, or advanced retrieval techniques.
* Experience integrating agentic components into large scale analytics or data platforms (e.g., Databricks, Snowflake).
* Background in data exploration or data modeling to support agent driven decision processes.
* Experience building AI focused prototypes or experimenting with emerging agentic patterns in rapid iteration environments.
* Familiarity with optimization techniques such as model routing, response validation layers, or inference acceleration.
* Familiarity with systems that handle sensitive data in accordance with HIPAA and federal security standards, including implementation of encryption, access controls, auditability, and governance for protected health information (PHI) within AI/LLM workflows.

Why Tria?
What defines the Tria brand is more than just our dedication to excellence in our craft; it's our incredible team of dedicated, talented, and passionate people that make Tria so exceptional. As people powering possible, we are all partners in our team's shared success.

As a company that cares about people, we seek to cultivate a culture in which all can thrive personally and professionally. We offer a top-tier benefits package to invest in your physical, mental, and financial health and wellness so that you can be your best self - at work and in life. At Tria, we are growth-minded, entrepreneurial in spirit, and committed to fostering a culture of inclusion and opportunity for all. Whatever your background, your role, your department, or stage in your professional journey, here you will have opportunities to learn new skills, seize new challenges, and advance your career as we grow.

California Consumer Privacy Act (CCPA)

We are committed to protecting your privacy. As part of our compliance with the California Consumer Privacy Act (CCPA), we want to inform you about how we collect, use, and protect your personal information during the job application process. For more details, please review