AI Engineer

Description

The company is a strategic AI partner to Fortune 500 companies.

The team supports a large AI-enabled software engineering transformation at a leading Financial Services organization.

The work runs on Claude, Claude on AWS Bedrock, OpenAI Codex, Cursor, and AWS.

Responsibilities

• Ship production code with coding agents every day: features, refactors, migrations, tests, and docs.
• Apply agents to legacy modernization and code or platform migrations across large, multi-repo enterprise codebases.
• Prove patterns on real projects, then turn them into guidance other teams can reuse.
• Review, test, and harden agent-written code until it meets production standards.
• Maintain standard agent setups: project memory files, custom slash commands, skills, subagents, and hooks.
• Build MCP servers and tool integrations that connect agents to repos, ticketing, CI/CD, docs, and internal APIs.
• Design context packages, prompt templates, and code indexing suited to large legacy systems.
• Diagnose and fix agent failures such as context overflow, tool misuse, and looping.
• Build headless and background agent workflows with CLIs and SDKs.
• Automate agent jobs in CI/CD: PR review, test generation, dependency upgrades, vulnerability fixes, and migrations.
• Build internal tools that let teams run agents across repos safely and easily.
• Automate quality checks on agent output, including tests and regression checks.
• Implement controls for agent use: permissions, sandboxing, command allowlists, secrets handling, and data protection.
• Connect agents to governed Claude access through AWS Bedrock, IAM, and the enterprise AI gateway.
• Build audit logs and usage tracking for agent activity and AI-written code.
• Work with InfoSec, Risk, and Compliance to turn financial regulatory and model risk rules into technical controls.
• Build telemetry and dashboards for usage, token spend, cost, and quality measures such as acceptance rate, cycle time, and defect rate.
• Run hands-on comparisons of new coding agents and models on real enterprise tasks, then recommend based on the data.
• Keep up with fast-moving agent tools and build working prototypes, not just slides.
• Secondary: document reference implementations, pair with engineering teams on adoption, and contribute reusable configs, templates, and examples to a shared internal repository.

Requirements

• Bachelor's or Master's degree in computer science, engineering, or a related field, or equivalent experience.
• 5+ years of professional software engineering, with strong Python and at least one more language such as TypeScript or Java.
• Daily hands-on use of Claude Code, Codex, Cursor, or similar agents to ship production code, with examples of substantial work delivered.
• Experience building MCP servers, custom tools, skills, subagents, or hooks.
• Strong skill in context and prompt design, task breakdown, and steering and verifying agent output.
• Experience building CI/CD automation and scripting agent workflows through CLIs or SDKs.
• Solid knowledge of Git workflows, testing, code review, and secure coding.
• Working knowledge of AWS services: Bedrock, IAM, Lambda, API Gateway, and S3.
• Strong analytical, problem-solving, and collaboration skills.
• Familiarity with coding agents such as Claude and Codex, and tools like Cursor.
• Preferred: experience with the Claude Agent SDK, Claude on Bedrock, or the OpenAI Agents SDK.
• Preferred: experience applying coding agents to large legacy modernization or migration programs.
• Preferred: experience building internal developer platforms or developer productivity tooling.
• Preferred: experience with AI gateways, LLM observability, and usage and cost tracking.
• Preferred: experience deploying AI coding tools in a regulated environment.
• Preferred: familiarity with SAST, DAST, and software supply chain security.
• Preferred: infrastructure as code with Terraform or CDK.
• Preferred: financial services experience in banking, capital markets, asset management, wealth management, or insurance.
• Preferred: AWS certifications such as Developer, Solutions Architect, or Machine Learning.

Conditions

Grade 8, 7, or 6.

Hands-on role: you build and ship with coding agents and the configurations, integrations, and automation that make them effective on enterprise codebases.

Estimated current pay range: $100,000 to $130,000. The range is not adjusted for the geographic differential of the location where the role may be filled.

Pay depends on skills, experience, training, licensure, certifications, and business needs, and hiring at or near the top of the range is not typical.

Benefits

• You may be eligible for a discretionary bonus for the current performance period.