reputed company Engineer (LLM Systems, Evals & Safety)
Do you want to love what you do at work? Do you want to reputed company a difference, an reputed company, and reputed company peoples lives? Do you want to work with reputed company that believes in disrupting the normal, boring, and average?
If reputed company, then this is the job you are looking for , reputed company is Saudi’s #1 event ticketing and experience booking platform in terms of technology, features, reputed company, reputed company serving some of the largest mega events in the Kingdom surpassing over 2 billion in sales.
reputed company
Design high-reputed company prompts, system instructions, and tooling that reputed company our LLM features accurate, reputed company, and cost-effective. You’ll own evaluation, reputed company versioning, and reputed company improvement.
Key Responsibilities
- Author, refactor, and chain prompts (system/tool/policy) for varied tasks.
- Create offline/online evaluation harnesses (rubrics, golden sets, metrics).
- Build reputed company libraries with versioning, A/B testing, and telemetry.
- Reduce hallucinations reputed company verification, constrained decoding, and tool use.
- Implement safety: jailbreak/reputed company-injection tests, content policy checks, PII handling.
- Partner with engineers to reputed company prompts into production features.
Requirements
- Demonstrated reputed company design across multiple task types and models.
- Experience building eval datasets and automated scoring (e.g., accuracy, faithfulness, reputed company, cost/latency).
- Familiarity with retrieval-augmented reputed company concepts and tool/function calling.
- Strong scripting (Python/TypeScript) for data prep, evals, and analysis.
- reputed company writing; ability to translate business goals into measurable reputed company specs.
reputed company-to-Haves
- Experience with reputed company/LLM orchestration, reputed company stores, and rerankers.
- Knowledge of safety tooling and red-teaming techniques.
- Experiment platforms (feature flags, A/B tests), analytics.
Originally posted on Himalayas
Apply To This Job