Production AI Engineer — Build Trusted AI Agents

Neura Market; Livingston (NJ); On-site; USD 143,000 - 210,000; Full time

Benefits offered by this job

Medical insurance

401(k) with employer match

Dental insurance

Vision insurance

Tuition Reimbursement

Paid time off

Job summary

CoreWeave is seeking an AI Engineer to design, build, and operate systems that engineers use during real customer incidents. You will own agent logic, retrieval, safeguards, and measurement, shipping your own services on production-grade infrastructure.

You will collaborate with engineers based on the live incidents, balancing AI with deterministic logic and ensuring safety and observability throughout the system.

Qualifications

• 3+ years of professional software engineering experience.
• Strong proficiency in Go or Python.
• Experience taking an AI application from prototype to production use.
• Hands-on experience with agent patterns and multi-step orchestration.
• Experience building and evaluating retrieval systems with held-out data.
• Observability for LLM apps, including tracing and latency.
• Kubernetes experience and CI/CD for deploying services.
• Experience integrating with third-party APIs and authentication.

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 consequential actions.
• Develop and evaluate retrieval over large historical support data sets.
• Balance AI and deterministic logic for production systems.
• Instrument systems for quality, cost, and adoption and plan next features.
• Deploy and operate services on Kubernetes and support them in production.

Skills

Go

Python

LLM engineering

Agent patterns

Retrieval systems

Observability

Kubernetes

CI/CD

APIs & auth

Job description

CoreWeave is seeking an AI Engineer to design, build, and operate systems that engineers use during real customer incidents. You will own agent logic, retrieval, safeguards, and measurement, shipping your own services on production-grade infrastructure.

You will collaborate with engineers based on the live incidents, balancing AI with deterministic logic and ensuring safety and observability throughout the system.