AI QA Trainer - Freelance Project
Meridial Marketplace is seeking an AI QA Trainer to perform model evaluation and quality assurance for large language models. The role involves adversarial red-teaming, hallucination detection, and developing test plans to ensure model safety and reliability. Candidates must have experience with Python, SQL, and LLM evaluation frameworks. This is a remote, contract-based position focusing on improving model reasoning and compliance.
50k new jobs listed every day. Install TAL to find more jobs like this.
Experience
Experience not specified
Function
Quality Assurance
Work mode
Remote, Singapore
Company
Tier 2
What you will work on
Meridial Marketplace is seeking an AI QA Trainer to perform model evaluation and quality assurance for large language models. The role involves adversarial red-teaming, hallucination detection, and developing test plans to ensure model safety and reliability. Candidates must have experience with Python, SQL, and LLM evaluation frameworks. This is a remote, contract-based position focusing on improving model reasoning and compliance.
TAL's take
Contractual role at an unfamiliar company with vague pay range, though task scope is well-defined.
The role provides clear responsibilities and technical expectations for AI evaluation and testing.
Watchouts
- contractor-style posting
- vague compensation
Must haves
- Shipped QA for ML/AI systems
- Safety/red-team experience
- Test automation frameworks like PyTest
- Hands-on work with LLM eval tooling
- Clear, metacognitive communication
Tools and skills
Nice to have: openai evals, rag evaluators, weights & biases.
About the company
unfamiliar company, default mid-tier