3 дня назад
AI Training and Prompt Engineering Specialist (AI)
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Training and Prompt Engineering Specialist (AI): Making YOlanda reliable as an AI concierge by designing prompts, evaluation systems, training data, and production code with an accent on LangChain, LangGraph, retrieval, and bilingual Spanish-English conversations. Focus on testing model behavior, red-teaming prompt injection and abuse, grounding financial answers, and shipping measurable improvements through Python-based evaluations.
Location: Remote, global; full-time with flexible working hours.
Company
operates a connectivity and distribution business with an AI concierge, YOlanda, built into the YO platform.
What you will do
- Own YOlanda’s system prompt, persona, tone, safety rules, refusal behavior, and action prompts for plans, top-ups, balances, offers, and support.
- Define the boundary between YOlanda and YOnC and create seamless handoffs between specialist models.
- Build few-shot examples, manage context, and prevent repeated questions or blank-prompt interactions.
- Create evaluation sets with test cases, pass conditions, and release-over-release scoring.
- Rank and critique outputs, produce reinforcement-learning and fine-tuning data, and fact-check plan prices, balances, and YOYO$ calculations.
- Develop Python evaluation tooling, work with streaming APIs, function calling and structured output, and maintain versioned prompts in Git.
Requirements
- At least 2 years of production experience building with large language models.
- Shippable Python skills for scripts, API clients, data handling, and tests.
- Experience with LangChain and LangGraph, including modifying existing graphs safely.
- Production retrieval experience with chunking, embeddings, reranking, grounding, and assessing when retrieval is inappropriate.
- Exceptional written English and bilingual Spanish and English proficiency to the same standard.
- Methodical experimentation: changing one variable, testing it, recording the result, and iterating.
Nice to have
- Fine-tuning experience with SFT, DPO, or LoRA.
- Experience with promptfoo, Braintrust, LangSmith, or DeepEval.
- Mobile, telecoms, or fintech experience.
- Editorial or linguistics training.
Culture & Benefits
- Flexible working hours and a global remote setup.
- Highly collaborative team focused on achieving shared goals.
- Corporate equipment provided for work.
- Competitive salary.
- Opportunities for personal and professional growth.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →
