Production AI Engineer

Noblesoft Technologies Inc.; California; On-site; USD 140,000 - 210,000; Full time

Job summary

Noblesoft Technologies Inc. is seeking an AI Developer to build and operate AI-enabled applications across customer experiences, employee productivity, and operations. You will own the lifecycle from design to production, focusing on secure integration, latency, cost, and observability.

The role emphasizes hands-on work with LLMs, retrieval-augmented generation, and end-to-end pipelines, plus collaboration with data, cybersecurity, and product teams to deliver measurable, scalable AI outcomes.

Qualifications

• Typically 4+ years of professional software engineering delivering AI/NLP data-intensive apps.
• Hands-on experience with LLM APIs, prompt design, and retrieval-augmented generation.
• Experience with SQL, containers, CI/CD, and cloud services.
• Strong habits: testing, secure coding, peer review, and production ownership.
• Ability to explain model limitations and trade-offs to nontechnical partners.

Responsibilities

• Build production applications using LLMs, retrieval-augmented generation, tooling, and deterministic logic.
• Develop secure APIs, services, adapters, and event-driven integrations for multiple enterprise domains.
• Implement robust security, validation, timeouts, retries, and escalation paths.
• Create evaluation datasets and automated tests for groundedness, relevance, and safety.
• Build CI/CD pipelines and productionRunbooks; monitor latency and cost; support incidents.

Skills

4+ years software engineering

AI/NLP production experience

LLM prompts and evaluation

Explain model trade-offs to non-tech

Education

Bachelor's degree in CS/Engineering/Data Science or related field

Tools

LLM APIs

SQL

CI/CD

Containers

Job description

Noblesoft Technologies Inc. is seeking an AI Developer to build and operate AI-enabled applications across customer experiences, employee productivity, and operations. You will own the lifecycle from design to production, focusing on secure integration, latency, cost, and observability.

The role emphasizes hands-on work with LLMs, retrieval-augmented generation, and end-to-end pipelines, plus collaboration with data, cybersecurity, and product teams to deliver measurable, scalable AI outcomes.