AI Process Engineer

Job Description Summary

You will identify, deconstruct, and re-implement high-value manual processes using AI agents, LLMs, and modern automation - replacing outdated bespoke tooling and undocumented expert intuition with transparent, verifiable, and scalable systems. You own the full arc: from ethnographic process discovery through to production agent orchestration with appropriate human oversight.

The Problem You'll Solve
Every organization has processes that live in the heads of a handful of experts. These workflows are described as "more art than science," rely on tools that haven't been updated since they were written, and resist automation because nobody has properly decomposed what's happening. The experts are protective, the documentation is tribal, and the tooling is brittle.

You will be the person who breaks these open.

Job Description

Job Responsibilities:

• Process Discovery & Knowledge Extraction
• Embed with domain experts to observe and document actual workflows (not the documented ones)
• Distinguish genuine expertise and edge-case reasoning from ritual, habit, and cargo-cutting
• Identify where "art" is pattern recognition that can be modeled, versus true judgment calls requiring human decision-making
• Produce formal process models from informal, oral-tradition knowledge
• Tool Replacement & Modernization:
• Audit legacy/bespoke tooling - identify what they do vs. what people think they do
• Design replacements using AI-native approaches (LLM pipelines, vision models, structured extraction) where appropriate, and conventional engineering where not
• Manage graceful deprecation of legacy tools without disrupting active operations

Agent Workflow Design & Orchestration:

• Architect multi-step AI agent workflows that decompose complex expert tasks into verifiable stages
• Define tool-use patterns, context management, and failure/fallback strategies for agents
• Build evaluation frameworks that compare agent output against expert baselines
• Implement confidence-gated escalation - the system knows what it doesn't know

Human-in-the-Loop Architecture:

• Design the HITL topology: which decisions require human approval, review, or override
• Define escalation thresholds, audit trails, and feedback loops that improve the system over time
• Ensure experts transition from "doers" to "reviewers and teachers" without loss of engagement or institutional knowledge
• Build calibration mechanisms so human reviewers stay sharp (not rubber-stamping)

Required Minimum Experience:

• Bachelor's degree from an accredited university or college
• Minimum of 5 years of experience in software/AI engineering with at least 2 years building LLM-based or agent-based systems
• Demonstrated ability to extract tacit knowledge from domain experts (process mining, cognitive task analysis, or equivalent)
• Experience designing and deploying AI agent orchestration (multi-step, tool-using, with evaluation)
• Strong systems thinking - can model a process end-to-end before writing a line of code
• Track record of replacing legacy systems without burning the house down

Valued Experience:

• Background in knowledge engineering, expert systems, or decision support
• Experience in Aerospace Industry or Aviation Regulatory organizations
• Familiarity with regulated or safety-critical environments where auditability matters

Traits :

• Diplomatic persistence - experts will resist. You earn trust before you gain access
• Decomposition instinct - you see a 40-step manual process and immediately think in phases, decision points, and verifiable intermediate states
• Healthy skepticism - you don't automate what you don't understand; you don't trust the documentation
• Builder pragmatism - you ship the 80% solution with good HITL, not the 100% solution never

The base pay range for this position is $152,000 to $202,000 per year. The specific pay offered may be influenced by a variety of factors, including the candidate's experience, education, and skill set. This position is also eligible for an annual discretionary bonus based on a percentage of your base salary/commission based on the plan. This posting is expected to close on July 6th, 2026.

GE Aerospace offers comprehensive benefits and programs to support your health and, along with programs like HealthAhead, your physical, emotional, financial and social wellbeing. Healthcare benefits include medical, dental, vision, and prescription drug coverage; access to a Health Coach from GE Aerospace; and the Employee Assistance Program, which provides 24/7 confidential assessment, counseling and referral services. Retirement benefits include the GE Aerospace Retirement Savings Plan, a 401(k) savings plan with company matching contributions and company retirement contributions, as well as access to Fidelity resources and planning consultants. Other benefits include tuition assistance, adoption assistance, paid parental leave, disability insurance, life insurance, and paid time-off for vacation or illness.

GE Aerospace (General Electric Company or the Company) and its affiliates each sponsor certain employee benefit plans or programs (i.e., is a "Sponsor"). Each Sponsor reserves the right to terminate, amend, suspend, replace or modify its benefit plans and programs at any time and for any reason, in its sole discretion. No individual has a vested right to any benefit under a Sponsor's welfare benefit plan or program. This document does not create a contract of employment with any individual.

Additional Information

Compensation Grade

SPB2

GE Aerospace offers a great work environment, professional development, challenging careers, and competitive compensation. GE Aerospace is an Equal Opportunities Employer. Employment decisions are made without regard to race, color, religion, national or ethnic origin, sex, sexual orientation, gender identity or expression, age, disability, protected veteran status or other characteristics protected by law.

GE Aerospace will only employ those who are legally authorized to work in the United States for this opening.

Relocation Assistance Provided: No