AI-Native Product Engineer - Senior

EY•Hartford, DC

3d•$106,900 - $200,600•Hybrid

About The Position

EY is hiring a Senior AI-Native Product Engineer for Challenger, a program that builds and tests new services enabled by AI. The engineer will work end to end, close to users, product decisions, and production code, turning emerging AI capabilities and demonstrations into durable products that people choose to use and trust. Small, dedicated teams test ideas in real conditions; solutions that show business value and operational readiness transition to the business for adoption and scale. Challenger Core develops shared technology, methods, and risk and quality guardrails, and teams contribute reusable tools and practices. The role involves understanding real user workflows, testing product hypotheses through specifications, prototypes, and small releases, and owning complete product slices across user experience, services, data, AI behavior, and enterprise integrations. The engineer shapes AI behavior, builds evaluations and instrumentation, and embeds responsible-use safeguards. They release and monitor production systems, respond to incidents, improve product quality, and make practical trade-offs among experience, quality, speed, reliability, and cost. The role requires 5+ years of relevant experience and a bachelor's degree in a relevant field. It requires end-to-end product delivery, strong full-stack capability, applied AI and evaluation experience, live-service ownership, user-centered practice, and sound engineering craft. The position is listed as anywhere in the country, requires up to 50% travel, and requires flexibility to work from an office in a hybrid capacity. EY offers a comprehensive compensation and benefits package; base salary ranges vary by office location.

Requirements

5+ years of relevant experience.
Bachelor’s degree in a relevant field.
Record of taking customer- or employee-facing software from an unclear concept through launch, learning, and adoption.
Strong full-stack capability across modern frontend, backend, API, data, and cloud technologies, demonstrated through shipped work.
Hands-on experience building products with large language models, retrieval, tools, or comparable AI application patterns.
Experience with automated testing and behavioral evaluation for systems with variable or probabilistic outputs.
Demonstrated responsibility for telemetry, debugging, reliability, incident response, recovery, and performance improvement of live services.
Experience working directly with users, designers, and product leaders to turn evidence into better product decisions.
Consistent record of clear specifications, maintainable code, thoughtful review, and sound technical trade-offs.
Ability to travel up to 50% and flexibility to work from an office in a hybrid capacity.

Nice To Haves

Experience building workflow automation or collaborative AI products that interact with real business systems.
Experience with identity, knowledge systems, permission-sensitive information, or regulated and confidential settings.
Strong instinct for clear interactions, accessibility, and reducing user effort in complex workflows.
Experience improving the quality, latency, reliability, or economics of production AI applications.
Startup experience, open-source contributions, or another clear example of high-agency product building.

Responsibilities

Work directly with users and domain experts to understand workflows, observe friction, and identify opportunities for AI.
Translate product hypotheses into concise specifications, prototypes, and small releases that produce evidence early.
Build complete product slices across the experience, services, data, AI behavior, and enterprise integrations.
Design AI instructions, context, retrieval, structured outputs, and tool use; select adaptation or tuning when supported by evidence.
Create representative tasks and automated evaluations to measure usefulness, correctness, safety, accessibility, and improvement.
Instrument user journeys to connect adoption and task success with system behavior, latency, failures, and cost.
Build responsible-use safeguards, including permission boundaries, secure data handling, human checkpoints, graceful degradation, recovery, and rollback.
Release incrementally, monitor live behavior, respond to incidents, and turn failures into lasting product and engineering improvements.
Balance experience, quality, speed, reliability, and cost, using deterministic software when it is more dependable.
Share proven components and evaluation assets with the broader platform while remaining accountable for performance in the product workflow.