Lead AI Platform Engineer (Player-Coach) – Newport Beach

Sweet James, LLP

Newport Beach (CA)

On-site

USD 200,000 - 250,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

401(k)

Dental insurance

Health insurance

Paid time off

Vision insurance

Job summary

Sweet James, LLP in Newport Beach, CA, seeks a Lead AI Engineer (player-coach) to own our in-house AI platform and guide the engineering team. You will define platform standards, translate roadmaps into delivery, lead design reviews, and ship production code weekly, while mentoring engineers and coordinating with product, legal, and operations.

On-site role with competitive compensation. The role requires 8+ years building production software, strong leadership, and hands-on expertise with

Qualifications

8+ years building production software.
Technical leadership track record as a technical lead on systems other engineers depended on.
Leadership experience through mentoring, design review, and ownership of team output (formal people management welcome but not required).
LLM production craft delivering systems to real users across prompt and tool design, retrieval, structured extraction, evaluation, and cost and latency tuning.
Production engineering stack: Python; TypeScript/Node; production SQL in Postgres; Docker; containerized cloud services (Azure preferred); CI/CD; monitoring.
Operations ownership, including on-call, incident reviews, and rollbacks.
Clear communication via design docs, runbooks, and plain-language explanations for non-engineers.

Responsibilities

Own AI platform architecture across document intake and filing, fact extraction, case search, the internal assistant and its agents, and voice agents.
Review major designs before implementation to ensure platform standards are met.
Translate roadmap into delivery by deciding how priorities set by the Chief Technology Officer and product leadership get built.
Define the shipping process, including code review, testing, and AI evaluation sets required for release.
Own uptime and reliability with monitoring, incident response, and access controls across the platform.
Ensure operational resilience so no single person is a dependency for critical systems.
Lead through coaching and engineering execution: allocate team capacity to CTO priorities, manage trade-offs, and hire engineers.
Ship production code weekly as an active player on the team.
Partner with legal, case management, and operations to decide what to automate next.
Measure automation outcomes using hours returned, error rates, and adoption.
Set access and compliance controls including least-privilege access, audit trails, and rules for which client and medical data may reach which model.