AI Software Engineer

Description

Credence is hiring an AI Software Engineer for its growing AI and Automation practice in Tysons, Virginia. This is a full-time hybrid position focused on building and deploying AI-powered, cloud-native solutions for federal government missions. The role is aimed at engineers with hands-on AI/ML experience who want to work with generative AI, LLMs, and agentic AI systems.

The role combines AI development with practical software engineering. You may work on LLM applications, AI agents, tool calling, cloud deployment, CI/CD, containerization, production monitoring, and performance optimization. You will also work with software engineers, data engineers, data scientists, and other stakeholders to turn requirements into working AI systems.

This opportunity may be a good fit for an early-career AI engineer with 1–5 years of hands-on AI/ML experience who already works with technologies such as Python, TypeScript, LLM APIs, AWS or GCP, Docker, Kubernetes, and modern AI frameworks. U.S. citizenship and eligibility for a DoD Secret clearance are required. The listed salary is $120,000–$150,000 per year.

Job at a Glance

Detailed Role Requirements & Responsibilities

Generative AI and LLM Development

A major part of the position involves working with generative AI and large language models.

You may be responsible for:

• Prototyping and improving AI-powered capabilities
• Working with large language models and AI APIs
• Selecting appropriate models for specific use cases
• Building applications around LLMs
• Adding tool calls through technologies such as Model Context Protocol (MCP)
• Testing and refining AI-powered features
• Using APIs from OpenAI, Anthropic, Google Gemini, and Amazon Bedrock

The role is focused on practical AI application development rather than only research or model development.

Agentic AI System Development

The position has a strong focus on agentic AI.

Responsibilities can include:

• Creating AI agents
• Supporting model selection
• Implementing tool calling
• Working with response synthesis
• Developing background or autonomous agent capabilities
• Supporting agent development throughout the software lifecycle

The posting specifically mentions technologies and frameworks including Agent2Agent Protocol, Mastra, Strands, AgentCore, and Gemini Agent Platform.

Software Engineering

Although this is an AI-focused position, strong software engineering practices are important.

The engineer will be expected to:

• Write clean and maintainable code
• Follow software engineering principles
• Build reliable and scalable applications
• Document technical work
• Use modern AI coding tools to improve development workflows
• Support reproducible development practices

AI knowledge alone is therefore not enough. Candidates should be able to demonstrate solid software development skills.

Cloud and Deployment

The role involves deploying AI applications using cloud and container technologies.

Relevant responsibilities include:

• Deploying applications on AWS or GCP
• Using Docker for application containerization
• Working with Kubernetes
• Supporting cloud-native application deployment
• Automating model deployment workflows
• Using Infrastructure as Code where appropriate
• Supporting CI/CD pipelines

GitLab CI is specifically mentioned as a desired CI/CD technology.

Production Monitoring and Optimization

The engineer will also be involved after AI systems are deployed.

This includes:

• Monitoring AI application performance
• Identifying performance problems
• Tuning systems when necessary
• Improving reliability
• Considering scalability as systems grow
• Supporting production AI applications

This is useful for candidates who have experience taking AI projects beyond prototypes and into real production environments.

Team Collaboration

The position involves working with multiple technical and stakeholder groups.

You may collaborate with:

• Software engineers
• Data engineers
• Data scientists
• Senior AI leaders
• Other project stakeholders
• Federal customers or clients

Strong communication and a client-oriented approach are specifically listed as requirements.

Professional Development

The role also provides an opportunity to learn from senior AI professionals. The posting describes mentorship, technical design reviews, and staying current with AI/ML developments as part of the position.

This can be valuable for engineers who already have practical AI experience but want to deepen their knowledge of agentic AI and modern AI application development.

Required Skills and Experience

The main requirements include:

• Bachelor’s or Master’s degree: A degree in Computer Science, AI/ML, or a related field is required.
• 1–5 years of AI/ML experience: Candidates should have hands-on experience delivering AI/ML solutions.
• Generative AI and LLM experience: You should have practical experience using generative AI and large language models.
• MCP and tool calling: Experience adding tool calls using MCP is required.
• Agentic AI experience: Familiarity with agentic frameworks such as Agent2Agent Protocol, Mastra, Strands, AgentCore, or Gemini Agent Platform is expected.
• AI APIs: Experience with OpenAI, Anthropic, Gemini, or Amazon Bedrock is important.
• TypeScript: Strong TypeScript skills are required.
• Python: Python proficiency is also required.
• Cloud platforms: Experience with AWS or GCP is expected.
• Docker and Kubernetes: Candidates should have experience deploying applications using container technologies.
• CI/CD: Familiarity with CI/CD pipelines, particularly GitLab CI, is required.
• AI coding tools: Experience with tools such as Claude Code, Codex, or Antigravity is listed.
• Communication: Strong communication and a client-oriented mindset are required.
• Citizenship and clearance eligibility: Candidates must be U.S. citizens with eligibility for a DoD Secret clearance.

Skills That Can Strengthen Your Application

The employer lists several preferred qualifications that can make an application stronger but should not be treated as core mandatory requirements.

These include:

• Experience with data engineering
• Data science experience
• UI/UX knowledge
• Cloud engineering
• Platform engineering
• Terraform
• OpenTofu
• AWS CDK
• CloudFormation
• Federal cybersecurity
• Risk Management Framework (RMF)
• FedRAMP
• Other relevant regulatory frameworks

Experience across several parts of the software ecosystem can help demonstrate that you understand how AI applications fit into a larger technical environment.

Industry Context & Career Advice

AI engineering is moving beyond simple model experimentation toward production applications that combine LLMs, software engineering, cloud infrastructure, APIs, and automated workflows. Agentic AI is an important part of this change because applications can use models together with tools and other services to complete more complex tasks.

For someone applying to this role, practical implementation experience is particularly valuable. A resume that only says “worked with AI” will be less useful than one that explains what AI application was built, which model or API was used, how it was deployed, and what problem it solved.

Cloud and software engineering skills can also make an AI engineer more versatile. Experience with AWS or GCP, Docker, Kubernetes, CI/CD, APIs, and production monitoring shows that you can help move AI systems from an experimental environment into a working application.

Because this role supports federal missions, familiarity with security and compliance can also become valuable as you progress. Preferred knowledge of RMF, FedRAMP, or federal cybersecurity can help distinguish candidates who understand the additional requirements involved in government technology projects.

What to Highlight on Your Resume

For this AI Software Engineer position, make the following areas easy to find on your resume:

• Generative AI and LLM projects
• AI agent development
• MCP or tool-calling experience
• OpenAI, Anthropic, Gemini, or Amazon Bedrock
• Python
• TypeScript
• FastAPI, LangChain, LangGraph, CrewAI, or related AI frameworks
• AWS or GCP
• Docker and Kubernetes
• CI/CD and GitLab CI
• AI coding tools
• Production AI deployments
• AI application monitoring and optimization
• Cloud-native development
• Collaboration with data scientists and software engineers

If you have built an AI application, describe the actual outcome rather than simply listing the technology.

For example:

Built and deployed an LLM-powered AI application using Python, TypeScript, and cloud infrastructure, integrating external tools through API-based workflows and monitoring production performance.

Only use this type of bullet if it accurately reflects your own experience. Add measurable results when you have reliable figures.

Interview Preparation

Prepare for questions that test both your AI knowledge and your ability to build reliable software.

How would you build an AI agent for a real business or government use case?

Be ready to explain how you would understand the requirements, select an appropriate model, define the agent’s tools, manage responses, test the system, and monitor it after deployment.

How do LLM tool calls work?

Review how an LLM can interact with external tools or APIs rather than generating an answer alone. If you have worked with MCP, prepare a practical example.

How would you choose between different LLM APIs?

Think about factors such as capability, latency, cost, reliability, security, context requirements, and the specific application.

How would you deploy an AI application to AWS or GCP?

Review your experience with cloud infrastructure, Docker, Kubernetes, CI/CD, environment configuration, monitoring, and production deployment.

How would you monitor an AI application after deployment?

Consider application performance, errors, latency, reliability, resource usage, model behavior, and the quality of responses.

Tell us about an AI/ML project you built.

Choose one project that demonstrates hands-on experience. Explain the problem, your role, technologies used, development process, deployment approach, and results.

How do you work with software engineers, data engineers, and data scientists?

Prepare an example showing how you communicated requirements, solved technical disagreements, divided responsibilities, or helped move a project forward.

How do you keep up with rapidly changing AI technology?

The role emphasizes current AI tools and innovation. Be prepared to discuss how you learn about new models, frameworks, agentic AI techniques, and development tools, and how you decide which technologies are actually worth using.

Advice for Applicants

This role is a strong match for candidates who already have practical AI/ML development experience and want to work more deeply with generative AI and agentic systems.

The biggest requirements to check before applying are the 1–5 years of hands-on AI/ML experience, generative AI and LLM experience, TypeScript and Python skills, cloud experience, containerization, and U.S. citizenship with eligibility for a DoD Secret clearance. If you do not meet the citizenship and clearance requirement, that is an important eligibility issue rather than simply a skill gap.

You do not need to have every preferred technology listed in the posting. If you have strong experience with the core AI, software engineering, and cloud requirements, make those strengths prominent and explain how quickly you have learned related tools.

When applying, position yourself as an AI software engineer who can build and deploy real applications, not just someone who has experimented with AI models. Show your hands-on projects, technical decisions, cloud deployments, AI integrations, and measurable results.

Salary and Benefits

The listed salary range is $120,000–$150,000 per year, with actual compensation depending on experience, education, certifications, skills, and qualifications. Listed benefits include health coverage, dental and vision insurance, a 401(k)/retirement plan, life insurance, paid time off, family leave, disability coverage, training and development, and wellness resources.