Senior AI Engineer, Release Engineering

Intercontinental Exchange Holdings, Inc.•Atlanta, GA

3d•Onsite

About The Position

The Senior AI Engineer is a full-stack engineer with strong AI and large language model expertise, embedded within ICE’s Release Engineering Development team. The team designs and maintains processes that improve infrastructure delivery through application development, data management, and automation. The role builds and operates an internal AI-powered developer platform and its agentic AI capabilities. The platform is central to ICE’s AI Development Life Cycle (AIDLC) and automates development, release, and operational workflows across engineering. It includes agents, skills, and MCP integrations for CI/CD, source control, ticketing, and deployment systems, designed with appropriate security, evaluation, and auditability for privileged access. The engineer will develop reliable agents and workflows, advance the AIDLC, and help teams adopt reusable AI capabilities. The role also owns platform reliability, security, governance, evaluation, and cost management, while collaborating with Engineering, Infrastructure, and release teams.

Requirements

Bachelor’s degree or an equivalent combination of education and experience.
At least 5 years of professional experience in software engineering, DevOps, or release engineering, including platform or internal tooling work.
Hands-on experience with CI/CD and Git-based source control platforms such as GitHub or Bitbucket; GitHub is preferred.
Understanding of agentic patterns, including planning, tool selection, multi-step tasks, agent-loop design, and failure modes.
Strong prompt-engineering and context-window management skills, including experience with skill definitions or scoped system prompts.
Working knowledge of AI security risks, including prompt injection.
Daily use of AI coding tools such as Claude Code, GitHub Copilot, Codex, Cursor, or similar products.
Treat agentic AI as a design discipline and demonstrate practical application of emerging LLM and agent capabilities.
Take ownership of reliability, security, and quality, and make failure modes explicit.
Collaborate effectively across engineering teams and build trust with skeptical teams.

Nice To Haves

Experience with agentic technologies such as LangChain, LlamaIndex, LiteLLM, or AutoGen, and judgment about when a leaner custom approach is appropriate.
Experience with Node.js/TypeScript, Go, and/or Python.
Demonstrated experience building and delivering at least one production or near-production agentic automation or process using LLM APIs such as Anthropic, OpenAI, or LiteLLM, with tool calling and structured output.
Practical experience with MCP or equivalent tool-calling frameworks, including schema design, agent-tool integration, and scope management.
Experience evaluating LLM outputs using evaluation sets, regression testing, and quality metrics.
Experience with retrieval-augmented generation (RAG) and vector databases.
Experience with cloud AI platforms such as Amazon Bedrock, Azure OpenAI, or Vertex AI.
Experience with internal developer platforms or platform-as-a-product models.
Frontend development experience with React or Angular.
Relational database design experience.
Experience with LLM observability tools.
Experience with infrastructure as code and configuration management tools such as Terraform, Ansible, Puppet, or Chef.
Experience working in regulated or audited environments.
Experience with Agile practices and automated testing.
Experience with containers and orchestration platforms such as Kubernetes or OpenShift, and proficiency in Linux environments.
Experience troubleshooting distributed systems, such as Kubernetes workloads, CI/CD pipelines, and message queues.

Responsibilities

Design, build, and maintain the agent platform, including its API, MCP integrations, and intent-routing logic.
Build MCP integrations for CI/CD, source control, ticketing, and deployment tools, with clear schemas, robust error handling and logging, and defined scope boundaries.
Build and maintain a skill and agent registry that matches user intent with the appropriate agent and context at runtime.
Maintain a modular architecture that allows agents, skills, and integrations to be added without disrupting existing capabilities.
Design multi-step, tool-using agents that select tools, reason across context, and produce reliable, structured output.
Author, test, and iterate on prompts, skill definitions, and context structures while managing context windows and token budgets.
Anticipate agent failures, context degradation, and prompt drift, and define recovery approaches.
Build release and CI/CD agents for pipeline triage, release-readiness checks, change documentation, and rollback assistance in partnership with release and development teams.
Curate and maintain the AIDLC, outline best practices, and champion the process across the company.
Enforce least-privilege and zero-trust access for agentic automation, with defined identities and per-tool permissions.
Design human-in-the-loop approval workflows for high-risk actions such as deployments, promotions, and rollbacks.
Protect against prompt injection, data leakage, and overprivileged agents.
Ensure audit logging, compliance, and data-handling controls for agent actions and model inputs.
Build and operate evaluation frameworks, including evaluation sets, prompt regression tests, and quality metrics for agents and skills.
Evaluate and select models while managing routing, caching, token budgets, and cost attribution.
Instrument agent runs with tracing and structured logging to support diagnosis of incorrect decisions.
Own platform reliability through health checks, runbooks, and explicit failure modes; support release tooling, CI/CD pipelines, and AI workflows in production.
Contribute to developer-facing interfaces, including chat integrations within existing communication tools and the skills catalog.
Drive adoption by mentoring teams, documenting reusable patterns, and gathering feedback from skeptical users and early adopters.
Translate workflow needs from Engineering, Infrastructure, and release teams into effective agents and skills.
Track emerging models and agentic use cases, and prototype relevant technologies.
Write clean, tested, and secure code; participate in code and design reviews; and document agent designs, prompt strategies, and platform decisions.