Remote AI Engineer: Production LLM & Agentic Features

Charity Navigator; Union City (NJ); On-site; USD 105,000 - 125,000; Full time

Benefits offered by this job

Health, Dental, Vision insurance

Life Insurance

Paid time off 20 days

401(k) matching

FSAs

Job summary

Charity Navigator, the world's largest independent nonprofit evaluator, is hiring a software engineer to ship production LLM-powered features that improve how donors search, compare, and understand 245,000+ nonprofits. You’ll join an existing team and contribute to AI-enabled capabilities from day one.

You will collaborate with senior engineers on system design, focus on reliability, and explore orchestration frameworks and vector stores to surface accurate ratings data while citing sources.

Qualifications

• Bachelor's degree or equivalent practical experience in CS/engineering/AI.
• 2–3+ years building ML models or AI-driven apps with Python.
• Experience with foundation models, prompt engineering, and orchestration frameworks.
• Experience with vector databases and RAG workflows for data retrieval.

Responsibilities

• Build and ship production LLM-powered features with prompt orchestration and tool calling.
• Develop API integrations and RAG workflows connecting data systems to vector search.
• Create evaluation infrastructure to catch regressions in AI features.
• Monitor production AI metrics: accuracy, latency, token cost, and hallucinations.
• Implement runtime safety guardrails within quality and compliance bounds.
• Evaluate models/tools and guide architecture decisions with leadership.
• Collaborate with non-technical stakeholders to scope AI initiatives.

Skills

Python programming

ML fundamentals

LLM & agentic systems

API integration

orchestration frameworks

Education

Bachelor's degree in Computer Science/Engineering/AI or related field

Tools

LangChain

LlamaIndex

pgvector

OpenSearch

MCP servers

Job description

Charity Navigator, the world's largest independent nonprofit evaluator, is hiring a software engineer to ship production LLM-powered features that improve how donors search, compare, and understand 245,000+ nonprofits. You’ll join an existing team and contribute to AI-enabled capabilities from day one.

You will collaborate with senior engineers on system design, focus on reliability, and explore orchestration frameworks and vector stores to surface accurate ratings data while citing sources.