Senior Software Engineer (Hybrid)

About the role

You will be at the center of an award-winning corporate culture at Wyetech, where your technical decisions directly influence our federal government customers' ability to solve complex real-world problems through technology. In this role, you own the end-to-end design and implementation of AI integration frameworks that power our next-generation agentic platforms. You will architect and build the foundational Python-based components of our proprietary Data Lake tool, JCRSD, ensuring they meet strict standards for security and scalability. You are responsible for developing Model Context Protocol (MCP) servers and reusable AI skills that integrate safely and reliably into larger autonomous systems. A core part of your ownership involves creating strict safety guardrails and patterns that allow our platform to leverage large language models without compromising operational integrity. You will coordinate extensively with disparate internal teams to expose their APIs and services to our autonomous agents, ensuring seamless communication and data flow. This position requires you to treat artificial intelligence as a complex software integration problem rather than a purely research-oriented challenge, focusing on robust deployment and maintainability. If you thrive in an environment where you can break technological barriers alongside a world-class team, this role is where you will make your most significant impact.

Key facts

What you'll do

Architect and maintain the core Python-based components of our JCRSD Data Lake platform, ensuring high performance and reliability in production environments.

Design and develop scalable container orchestration workflows using Kubernetes to deploy AI integration services with zero-downtime and resilience.

Build and maintain Model Context Protocol (MCP) servers that enable secure and standardized communication between our agents and external data sources.

Implement reusable AI skill modules that can be composed dynamically by autonomous agents to solve diverse client problems.

Establish strict safety guardrails and validation layers to ensure AI-generated actions remain within defined ethical and operational boundaries.

Integrate third-party open-source capabilities and large language models into our frameworks while adhering to federal compliance and security standards.

Collaborate closely with internal product and engineering teams to expose APIs and services, ensuring our autonomous agents can interact with legacy and modern systems.

Optimize the end-to-end agentic platform for scalability, monitoring, and debugging to support rapid iteration and troubleshooting.

Write clean, maintainable, and tested code that aligns with industry best practices and supports long-term platform evolution.

Act as a technical leader in the design reviews for AI integration layers, guiding junior engineers and ensuring architectural consistency across projects.

Translate complex client requirements into technical specifications that drive the development of secure and efficient AI integration solutions.

Continuously evaluate emerging open-source tools and LLM frameworks to identify opportunities for improving our platform's capabilities and performance.

Requirements

You must be a United States Citizen due to federal contract requirements, and you must possess or be able to obtain appropriate security clearance, such as Active TS/SCI with agency-appropriate polygraph.

You must have a Bachelor's degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.

You must have a proven track record of at least five years in software engineering roles, with demonstrable experience in Python development.

You must have hands-on experience with container orchestration platforms, specifically Kubernetes, and with deploying scalable microservices.

You must be proficient in writing and maintaining infrastructure as code, utilizing tools that ensure secure and repeatable deployments.

You must have a deep understanding of how to integrate large language models and third-party AI services into production software systems.

You must have experience designing and implementing APIs and MCP servers that enable interoperability between distributed systems and AI agents.

You must be able to obtain and maintain government security clearances, indicating your eligibility for positions requiring public trust.

Nice to have

Experience with building and deploying autonomous agent frameworks and understanding how to integrate them with existing enterprise systems.

Familiarity with the Model Context Protocol (MCP) and its application in connecting AI models to data sources and services.

Contributions to open-source projects related to AI, data platforms, or security-focused software.

Practical notes

This role requires United States Citizenship and the ability to obtain appropriate security clearance, such as Active TS/SCI with agency-appropriate polygraph.

The position is based in Columbia, Maryland, and operates on a hybrid schedule in alignment with team and project needs.

Employment is full-time, and successful candidates are expected to commit to the long-term strategic goals of the platform and the federal clients we serve.

The role is exempt and requires consistent availability during standard business hours to coordinate with government stakeholders and internal engineering teams.

Candidates must be legally authorized to work in the United States without sponsorship now or in the future for this position.