AI Incident Engineer: Build Production-Grade AI Agents

FDE Times; Livingston (NJ); On-site; USD 143,000 - 210,000; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

Life Insurance

Disability insurance

Flexible Spending Account

Health Savings Account

Tuition Reimbursement

Employee Stock Purchase Program

Mental wellness benefits

Family-forming support

Parental leave

Childcare support

401(k) with employer match

Flexible PTO

Catered lunch

Casual work environment

Innovative disruption culture

Job summary

CoreWeave is seeking an AI Engineer to design, build, and operate AI-driven systems used during real customer incidents. You will own agent logic, retrieval, safeguards, and production behavior, working closely with engineers who rely on your work.

You will balance deterministic and AI components, ship your services on Kubernetes, and collaborate with support engineers and domain experts to optimize automation while maintaining safety and reliability.

Qualifications

• 3+ years of professional software engineering experience with Go or Python.
• Experience taking an AI application from prototype to production.
• Hands-on experience with agent patterns: tool/function calling, multi-step orchestration, handling incorrect model output.
• Experience building and evaluating retrieval systems against held-out data.
• Experience designing automation controls for production systems (approval steps, idempotency, audit trails).
• Experience diagnosing failures in LLM applications and fixing root causes.
• Experience with observability for LLM apps (tracing, cost, latency).
• Working knowledge of Kubernetes and deploying services through CI/CD.
• Experience integrating with third-party APIs (authentication and secrets handling).

Responsibilities

• Design and build AI agents that investigate and act on real customer issues.
• Build safeguards grounding model output in authoritative data and require human approval for critical actions.
• Develop and evaluate retrieval over large historical support data.
• Balance AI and deterministic logic for robust systems.
• Instrument systems for quality, cost, and adoption and iterate on future work.
• Deploy and operate services on Kubernetes and support them in production.

Skills

Go or Python

AI deployment

Agent patterns

Retrieval systems

Automation controls

LLM observability

Kubernetes

CI/CD

API integration

LLM debugging

Tools

Kubernetes

CI/CD

Job description

CoreWeave is seeking an AI Engineer to design, build, and operate AI-driven systems used during real customer incidents. You will own agent logic, retrieval, safeguards, and production behavior, working closely with engineers who rely on your work.

You will balance deterministic and AI components, ship your services on Kubernetes, and collaborate with support engineers and domain experts to optimize automation while maintaining safety and reliability.