POSITION OVERVIEW
Leading EDJE is seeking a highly skilled AI Engineer to help solve complex business challenges for our clients, ranging from mission-critical systems to efficiency improvements.
This is not a model-training or traditional data science role. We’re hiring an engineer to embed agentic AI tooling directly into how we build, test, review, and ship software. You’ll play a key role in defining how our engineering teams work alongside AI agents day-to-day, establishing workflows, guardrails, evaluations, and internal tooling that enable faster delivery without compromising code quality, security, or maintainability.
We’re looking for someone who has already leveraged agentic coding tools to ship real, production-grade systems and is excited to scale that impact across an entire engineering organization.
Our ideal candidate brings a strong passion for problem-solving, a commitment to delivering exceptional solutions, and a humble, team-first mindset. You embrace continuous learning and challenge conventional approaches, knowing that innovation comes from curiosity, experimentation, and iteration. You thrive in collaborative, fast-paced environments and are energized by working at the intersection of software engineering and emerging AI capabilities.
This full-time, salaried position offers flexibility in work location, with an expectation to collaborate during core hours of 9 AM – 4 PM EST.
If you’re an experienced AI Engineer excited to help shape how modern engineering teams leverage AI and want to do so alongside a thoughtful, creative, and highly collaborative team, this could be the right next step, even if you’re not actively looking.
CONSULTING ENVIRONMENT
As part of Leading EDJE, you’ll have the opportunity to work across a variety of client projects. We value developers who are passionate about learning, adaptable to new challenges, and committed to delivering outstanding results no matter the client or technology. We’re seeking experienced, well-rounded Senior Developers who can thrive independently in client-facing environments, collaborate effectively, and deliver quality, scalable solutions.
RESPONSIBILITIES
Design and implement agentic workflows across the full SDLC, including planning, scaffolding, development, testing, code review, debugging, deployment, and incident response.
Build and maintain AI-enabled tooling and integrations, such as skills, commands, custom agents, MCP servers, CI/CD hooks, and evaluation frameworks that measure and improve agent output over time.
Establish and uphold standards for AI-assisted code quality, including testing strategies, review practices, observability, and security when agents are authoring or modifying code.
Act as a hands-on contributor by shipping production-grade software and infrastructure, using agentic tools to deliver real features, not just advising on best practices.
Coach and mentor engineers on effective agentic development practices, including context management, task decomposition, validation techniques, and appropriate use of AI tools.
Measure and iterate on impact, using data such as cycle time, defect rates, review burden, and agent effectiveness to continuously refine workflows and tooling.
Collaborate closely with Security, Platform, and Data/ML teams to ensure AI-assisted development is safe, auditable, and aligned with broader engineering strategy.
Demonstrate a commitment to continuous learning by proactively exploring emerging AI capabilities, experimenting with new tools and techniques, and sharing knowledge across the organization.
Communicate effectively with both technical and business stakeholders, representing Leading EDJE with professionalism and delivering high-quality solutions independently when needed.
QUALIFICATIONS
Demonstrated experience shipping production software with significant use of agentic AI tools. You can clearly articulate what the agent handled, what you owned, and how you ensured quality and reliability.
Strong software engineering fundamentals, including system design, testing, code review, and operating production systems.
Deep, hands-on familiarity with modern agentic coding tools (e.g., Cursor, Claude Code, Copilot, Codex or similar) and a practical understanding of their strengths, limitations, and failure modes.
Experience with prompt and context engineering, including structuring inputs, managing context, and designing effective agent workflows.
Ability to evaluate non-deterministic AI outputs, including building or working with evaluation frameworks, regression tests, or quality benchmarks.
Strong judgment around code quality and trade-offs, ensuring AI-generated code remains secure, maintainable, and production-ready.
Experience with cloud platforms (AWS, Azure, or GCP) and modern development practices, including CI/CD and Infrastructure as Code.
Strong communication skills, with the ability to document patterns, influence teams, and coach engineers on effective AI-assisted development.
Experience working in Agile environments and collaborating with cross-functional teams.
Minimum 5+ years of professional software engineering experience, ideally in client-facing or consulting environments.
NICE TO HAVE
Experience building or integrating with MCP (Model Context Protocol) or similar tool ecosystems.
Hands-on experience with agent frameworks (e.g., LangGraph, DSPy, PydanticAI, or similar).
Background in Developer Experience, Platform Engineering, or build/release systems.
Familiarity with LLM security considerations, such as prompt injection, dependency risk, and secret management.
Prior experience as a tech lead or staff engineer driving adoption of new tools or practices across teams.
Contributions to open-source AI tooling, agent frameworks, or evaluation systems.