Context Engineer

Why USAA?

At USAA, our mission is to empower our members to achieve financial security through highly competitive products, exceptional service and trusted advice. We seek to be the #1 choice for the military community and their families.

Embrace a fulfilling career at USAA, where our core values – honesty, integrity, loyalty and service – define how we treat each other and our members. Be part of what truly makes us special and impactful.

We are proud to support active-duty military spouses. USAA roles may offer remote or hybrid flexibility for active-duty military spouses consistent with applicable policy and business needs.

The Opportunity

As a dedicated Context Engineer are you fascinated by the frontier of generative AI, LLMs, and autonomous agents? Do you bridge the gap between human intent and machine execution? We are looking for a forward-thinking Context Engineer to join our team—someone who doesn't just build with AI, but shapes how business context, data, and logic are structured to drive real-world impact. In this role, you will sit at the intersection of business strategy, data science, and engineering, acting as the architect of prompts, workflows, and agent behaviors. If you are passionate about rapidly iterating on AI solutions, optimizing model outputs, and ensuring safe, compliant agent control design in a fast-paced environment, we want you on our team.

 What you will do:

• Collaborates closely with cross-functional business, data science, and engineering teams to translate complex business objectives into effective AI and agentic workflows.
• Designs, tests, and optimizes prompt architectures, context windows, and retrieval-augmented generation (RAG) pipelines to maximize LLM performance and accuracy.
• Engineers and monitors autonomous or semi-autonomous AI agents, participating in iterative solution design and continuous refinement.
• Applies qualitative and quantitative evaluation frameworks to assess model behavior, hallucinations, latency, and overall output quality against business use cases.
• Adheres to rigorous risk, safety, and agent control design standards to ensure ethical AI deployment, alignment, and compliance with regulatory standards
• Synthesizes complex AI outputs and multi-modal data insights into clear, actionable recommendations and communication materials for peer review and stakeholder alignment.
• Documents system instructions, prompt templates, agent logic, and testing frameworks comprehensively to facilitate transparent peer reviews and compliance audits.
• Explores and rapidly adopts emerging generative AI technologies, frameworks, and tooling to continually enhance solution strategies.
• Delivers findings and demonstrates agent capabilities in a manner that influences mid-level management, secures stakeholder buy-in, and accelerates AI adoption.
• Ensures risks associated with AI operations, data leakage, and automated business activities are effectively identified, measured, monitored, and controlled.

What you have:

• Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, Information Systems, or a related technical/quantitative field; OR 4 years of relevant education and/or technical experience.
• 2+ years of hands-on experience working with modern AI/ML technologies, data analytics, or software development—specifically involving LLM applications, prompt engineering, or workflow automation—OR an Advanced degree in Computer Science, AI, Data Science, or a related quantitative/technical discipline.
• Demonstrated experience with Large Language Models (LLMs), prompt engineering patterns (e.g., Chain-of-Thought, few-shot), and working with major foundation model APIs or open-weights models.
• Practical familiarity with AI orchestration frameworks and toolsets (e.g., LangChain, LlamaIndex, Semantic Kernel, or custom agent frameworks) and vector databases.
• Proficiency in Python and modern data manipulation tools, with the ability to query structured/unstructured data sources (SQL, APIs) to feed context into AI pipelines.
• Solid understanding of AI risk management, guardrails, security best practices (e.g., mitigating prompt injection, data privacy), and agent control design.
  

Compensation range: The salary range for this position is: $77,120 - $147,390

USAA does not provide visa sponsorship for this role. Please do not apply for this role if at any time (now or in the future) you will need immigration support (i.e., H-1B, TN, STEM OPT Training Plans, etc.).

Compensation: USAA has an effective process for assessing market data and establishing ranges to ensure we remain competitive. You are paid within the salary range based on your experience and market data of the position. The actual salary for this role may vary by location.

Employees may be eligible for pay incentives based on overall corporate and individual performance and at the discretion of the USAA Board of Directors.

The above description reflects the details considered necessary to describe the principal functions of the job and should not be construed as a detailed description of all the work requirements that may be performed in the job.

Benefits: At USAA our employees enjoy best-in-class benefits to support their physical, financial, and emotional wellness. These benefits include comprehensive medical, dental and vision plans, 401(k), pension, life insurance, parental benefits, adoption assistance, paid time off program with paid holidays plus 16 paid volunteer hours, and various wellness programs. Additionally, our career path planning and continuing education assists employees with their professional goals.

For more details on our outstanding benefits, visit our benefits page on USAAjobs.com.

Applications for this position are accepted on an ongoing basis, this posting will remain open until the position is filled. Thus, interested candidates are encouraged to apply the same day they view this posting.

USAA is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran.