AI Аналитик

Mayflower is a technology company building large-scale entertainment products for a global audience. Our platforms serve millions of users worldwide and rank among the top-50 most visited websites globally. For more than 10 years, we’ve been creating reliable, high-performance solutions at the intersection of product, engineering, and entertainment.

We build production agentic systems that read from and write to internal resources. You will design, ship, and measure them.

What you’ll do

• Ship end-to-end: Take agentic workflows from prototype to production, build user interfaces around them.

• Design agent architecture: Define tools, memory, retrieval strategies, and human-in-the-loop handoffs.

• Integrate systems: Expose internal tools and data via MCP servers and APIs with least-privilege access.

• Evaluate performance: Build trace-based evals and golden datasets to catch regressions across full agent runs.

• Operate in production: Implement tracing, token budgets, cost controls, and safety guardrails.

• Scope problems: Work with domain owners to identify where agents add value —and push back when a simpler solution is better.

Requirements

• Proven experience shipping production LLM agents or automations.

• Strong Python and/or TypeScript skills (clean code, automated testing, code reviews).

• Deep familiarity with current frontier models: cost, latency, capabilities, and trade-offs.

• Hands-on experience with tool calling, MCP, and modern retrieval (agentic/hybrid search, long-context vs. vector stores).

• Strong system design skills covering failure modes, latency, cost, and security.

• A passion for upskilling others — running demos, sharing workflows, and helping teams across the company adopt AI practically.

Nice to have

• Docker and Kubernetes / OKD (OpenShift).

• LLM gateways, observability tools, and eval frameworks.

• Experience integrating legacy or enterprise systems.
  

Conditions

We know that great talent deserves great conditions, so here’s what you can expect when joining us:

• EU-based employment contract and a 3-year Cyprus work visa with full support for your relocation and visa processes, including assistance for your family.

• EU passport. Opportunity to obtain an EU passport after 4 years of residence

• Full relocation package: flights to Limassol for you and your family, a company-covered apartment for the first month, and full relocation support to make your move smooth and hassle-free.

• Provident fund (Cypus): a long-term savings plan co-funded by you and the Company together (available after probation) that grows throughout your time with us in Cyprus.

• Transparent performance reviews twice a year, with bonus opportunities and salary adjustments.

• Private medical insurance for you and your family

• Corporate mobile plan (unlimited in Cyprus with roaming included)

• Mindfulness & well-being support, including psychological assistance with 50% coverage.

• 50% coverage of school and kindergarten fees for your children.

• Fully covered sports benefits, and also access to in-house electric scooters and bike rentals

• Professional growth support: language courses, conferences, training programs, and coaching.

• Peer recognition program: receive and share kudos for great work.

• A fully equipped office in Limassol’s city center, with everything you need for deep work and collaboration.

• Free breakfasts and lunches in the office and an in-house coffee bar with high-quality drinks and a health bar stocked with nutritious snacks.

• A strong engineering culture: international teams, corporate events, team-building, and hackathons — because great work happens in great communities.

Компания "Эксцельсиор" - лидер среди аутсорсинговых компаний, предлагает свои услуги уже на протяжении 13 лет.

Нас отличают доверие клиентов и уважение сотрудников. Мы успешно оказываем услуги в 46 регионах России, в настоящее время в нашей команде уже более 8 000 человек и мы продолжаем активно расти и развиваться.

В связи с ростом внутренних процессов и необходимостью снизить рутину, мы ищем,в нашу команду, специалиста по автоматизации бизнес-процессов (AL\No-code Engineer)

Чем предстоит заниматься:

Автоматизировать внутренние процессы на no-code/low-code платформах (n8n, Make, Dify или аналоги).
· Создавать внутренних AI-ботов по базе знаний компании (регламенты, инструкции, шаблоны документов).
· Строить RAG-сценарии: поиск ответов по загруженной базе знаний.
· Интегрировать сервисы через API и вебхуки: CRM, Slack, MS Teams, корпоративная почта.
· Подключать и настраивать API языковых моделей (OpenAI, YandexGPT, Anthropic).
· Готовить текстовые данные: очистка документов, форматирование в Markdown/TXT.
· Переводить требования отделов в технические сценарии для ботов и автоматизаций.
· Контролировать лимиты расходов на внешние API.
· Запускать MVP в короткие сроки с минимальным бюджетом.

Мы ожидаем от кандидата:

- опыт работы от 1 года в автоматизации процессов или разработке чат-ботов

- Энергичность и коммуникативность

- Желание принести финансовый результат

- Уверенное владение no-code\low-code (n8n, Make, Dify или аналоги)

- Понимание принципов работы API ( OpenAl? YandexGPT, Anthropic) и технологии RAG

- Опыт интеграции сервисов через API, вехбуки (CRM, Slack, MC Teams, корпоративная почта)

- Навык структурирования и подготовки текстовых данных

- Наличие портфолио

- Наличие свидетельства об окончании профильных курсов или сертификатов по AI- интеграции, no-code разработке или основам Python - будет вашим преимуществом

Что предлагаем:

• график работы: 5/2, с 9 до 18 ( пт до 17)
• официальное трудоустройство по ТК РФ с 1-го дня
• прозрачную и конкурентную З/П
• ДМС через 1 год работы
• возможность участвовать в программе "карьера в Эксцельсиор"
• работу в стабильной и надёжной компании, реальные возможности роста и развития
• активную корпоративную жизнь.

Приглашаем присоединиться к нашей команде!

We're looking for an experienced Applied AI Engineer to join our Growth team and help build operations automation systems for our global mobility platform. If you're excited about applying machine learning to customer support, document verification, and fraud detection challenges across Bolt's 200M+ customers, you'll find plenty of impactful work here.

About us

With over 200 million customers across 50+ countries and 850+ cities, Bolt is one of the fastest-growing tech companies in Europe and Africa — powered by 4.5+ million partners on our platform, 4,000+ employees globally. And it's all thanks to our people.

We believe in creating an inclusive environment where everyone is welcome, regardless of race, colour, religion, gender identity, sexual orientation, national origin, age, or ability.

Our ultimate goal is to make cities for people, not cars — and we need your help on this mission!

About the role

Every new customer and order at Bolt can trigger an operational decision: a refund, a document check, an account review, a ruling in a dispute. Our teams already use AI on top of existing processes to make them faster and more accurate. Many of those processes need a redesign from the ground up, and a design that gets better with every decision it makes.

You start with customer support for all users, then move to document verification & fraud detection. After that, any process with high decision volume and a recorded outcome is in scope.

You are hands-on. You ship the product and own the result.

Main tasks and responsibilities

• Redesign processes. Mine an area's systems of record, interview the people who run it, and decide which steps become software, agents or human checkpoints.

• Define what great looks like. Turn real cases and human decisions into test sets, and turn every new failure into a regression test.

• Build checks that are hard to game. Calibrate LLM judges against human labels, keep them apart from programmatic checks, and guard cost and payouts.

• Run the improvement loop across policies, prompts, tools and models. Add fine-tuning where a better policy is not enough.

• Own the rollout gates. Decide what ships, run the A/B test, and feed the live result back into the test sets.

• Codify what works so other teams can run it without you.

You are measured on how many decisions you automate while raising their quality.

About you

• You come from software engineering, ML or data science, and you have shipped and operated a system that calls LLMs.

• You have built an evaluation suite for an LLM or agent system and used it to decide what ships.

• You have spent dozens of hours in agent traces finding where decisions went wrong, and fixed them.

• You have designed an LLM judge, measured its agreement with human labels, and fixed it when the two disagreed.

• You know how verifiers get gamed, and have caught a case of reward hacking in your work.

• You can design an A/B test, read its result, and explain to an operations lead why the offline tests predicted something different.

• You know when a rule, a classic ML model or a human beats an LLM, and you can show the cost trade-off.

• You write clearly in English. Your reports pair a ceiling estimate with a realistic one.

Nice to have:

• Hands-on post-training: RLVR, GRPO or DPO, reward modelling, LoRA etc.

• Program optimisation frameworks such as GEPA, DSPy or TextGrad.

• RL environment or gym design with programmatic grading.

• Operations automation at a marketplace, fintech or trust and safety team.

• Strong SQL, and comfort working in codebases you did not write.

This role is not for you if you want to train frontier models, need a finished spec before you start, or prefer benchmark scores to live results.

Why you'll love it here

• Accelerate your professional growth with unique career opportunities.

• Enjoy a rewarding salary and stock options, knowing that as Bolt succeeds, so do you.

• Take care of your physical and mental health with our wellness perks.

• Celebrate 5 years at Bolt with a 1-month paid sabbatical to recharge.

• Connect with colleagues at annual company events and smaller team gatherings.

• Work on-site at our Tallinn HQ, next to the operations and engineering teams whose decisions you automate.

Some perks may differ depending on your location and role.

At Bolt, using AI daily is a baseline expectation for everyone. If there's a faster, smarter way to do your work, we expect you to find it. You're still responsible for the output, so the standard stays high when using AI tools.

Experience is great, but what we really look for is drive, intelligence, and integrity. So even if you don't tick every box, please consider applying!

Everyone is welcome
Bolt is an equal opportunity employer. We are committed to building a diverse and inclusive workplace where all qualified applicants are considered for employment without regard to race, colour, nationality, religion, gender or gender identity, sexual orientation, age, or disability.

We welcome applications from all backgrounds and are happy to make reasonable accommodations throughout our hiring process. If you require any adjustments, please let us know