> Markdown version of [/jobs/ext/3684758-ai-engineer](https://www.wearedevelopers.com/jobs/ext/3684758-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Engineer - **Company:** Fractal Analytics - **Location:** United States - **Experience:** Expert - **Salary:** $100,000.0 - $130,000.0 - **Contract:** Permanent contract - **Skills:** Java (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Amazon S3, Audit Trail, Configuration Management, Code Generation, Code Review, Cyber Security, Continuous Integration, Cursor, Identity and Access Management, Python (Programming Language), Machine Learning, Systems Development Life Cycle, OpenAI, Secure Coding, Software Engineering, TypeScript, Software Vulnerability Management, GitHub Copilot, Large Language Models, Claude Code, Prompt Engineering, AI Coding Agents, Usage Tracking, Git Flow, Information Technology, Production Code, Claude, Functional Programming, Api Gateway, OpenAI Codex, Terraform, Agent SDK, Prompt Templates, Static Application Security Testing, Code Migration, Dynamic Application Security Testing - **Published:** October 11, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=cb715ed4f9bf1243 ## About the Role We are seeking a hands-on AI Engineer with deep, daily experience using and extending AI coding agents to support a large-scale AI-enabled software engineering transformation within a leading Financial Services organization. This role is about building and shipping: using Claude Code, Codex, Cursor, and similar tools to deliver production code, and engineering the configurations, integrations, and automation that make those agents effective on enterprise codebases. The successful candidate will work in an ecosystem built on Claude (including Claude Code and Claude on AWS Bedrock), OpenAI Codex, Cursor, and AWS. Should be familiar with Coding agents- Claude, Codex and tools like Cursors etc., * Bachelor's or Master's degree in Computer Science, Engineering, or a related discipline (or equivalent experience). * 5+ years of professional software engineering experience, with strong proficiency in Python and at least one additional language (e.g., TypeScript, Java). * Proven, daily hands-on use of Claude Code, Codex, and Cursor or similar agents to deliver production code, with examples of non-trivial work shipped. * Experience building MCP servers, custom tools, skills, subagents, or hooks. * Strong grasp of context and prompt design, task decomposition, and how to steer and verify agent output. * Experience building CI/CD automation and scripting agent workflows via CLIs or SDKs. * Solid grounding in Git workflows, testing, code review, and secure coding practices. * Working knowledge of AWS (Bedrock, IAM, Lambda, API Gateway, S3). * Excellent analytical, problem-solving, and collaboration skills., * Experience with the Claude Agent SDK, Claude on Bedrock, or the OpenAI Agents SDK. * Experience applying coding agents to large-scale legacy modernization or migration programs. * Experience building internal developer platforms or developer productivity tooling. * Experience with AI gateways, LLM observability, and usage/cost tracking. * Experience deploying AI coding tools in a regulated environment. * Familiarity with SAST/DAST and software supply chain security. * Infrastructure as code experience (Terraform, CDK). * Financial Services domain experience across Banking, Capital Markets, Asset Management, Wealth Management, or Insurance. * AWS certifications (Developer, Solutions Architect, or Machine Learning ## Description Hands-On Delivery with Coding Agents * Use coding agents (Claude Code, Codex, Cursor, GitHub Copilot, and similar) daily to deliver production-quality code: features, refactors, migrations, tests, and documentation. * Apply agents to legacy modernization, code migration, and platform migration work on large, multi-repo enterprise codebases. * Serve as the reference implementer: prove out patterns on real projects, then codify them for other teams. * Review, test, and harden agent-generated code to production standards. Agent Configuration & Customization (Build) * Build and maintain standardized agent configurations: project memory files (CLAUDE.md, AGENTS.md, Cursor rules), custom slash commands, skills, subagents, and hooks. * Develop MCP servers and tool integrations connecting agents to internal systems (repos, ticketing, CI/CD, documentation, internal APIs). * Engineer context packages, prompt templates, and codebase indexing approaches tailored to large and legacy environments. * Tune agent behavior and diagnose failure modes such as context overflow, tool misuse, and looping. Agent-Driven SDLC Automation * Build headless and background agent workflows using CLIs and SDKs (Claude Code headless mode, Claude Agent SDK, Codex CLI). * Implement agent automation in CI/CD pipelines: automated PR review, test generation, dependency upgrades, vulnerability remediation, and migration jobs. * Build internal tooling and wrappers that make agents easy and safe to run across repos and teams. * Automate the measurement and evaluation of agent output quality, including tests and regression checks on agent-generated changes. Security, Governance & Guardrails (Implementation) * Implement technical controls for safe agent usage: permission models, sandboxing, command allowlists, secrets handling, and data-exposure protections. * Integrate agents with governed Claude access through AWS Bedrock, IAM, and the enterprise AI Gateway. * Build audit logging and usage tracking for agent activity and AI-generated code. * Partner with InfoSec, Risk, and Compliance to translate Financial Services regulatory and model risk requirements into enforceable technical controls. Telemetry, Evaluation & Tool Benchmarking * Build telemetry pipelines and dashboards for usage, token consumption, cost, and quality metrics (acceptance rates, cycle time, defect rates). * Run hands-on bake-offs of emerging coding agents and models against real enterprise tasks; produce data-driven recommendations. * Stay current on rapidly evolving agentic coding tools and bring working prototypes, not slideware. Knowledge Sharing (Secondary) * Document reference implementations, and pair with engineering teams to unblock adoption. * Contribute reusable configs, templates, and examples to a shared internal repository.