Мы — аккредитованная IT-компания, которая является экспертом в области облачной IT-инфраструктуры и автоматизации бизнеса. В связи с ростом числа проектов и задач нам требуются AI Engineer / Python-разработчик (LLM, RAG, AI Agents).

Рассматриваем сотрудничество по договору ГПХ или с самозанятым специалистом. На текущем этапе постоянную загрузку гарантировать не можем: в отдельные периоды задач может быть много, в другие — существенно меньше. Поэтому вакансия подойдет специалисту, которому интересен проектный формат сотрудничества.

Чем предстоит заниматься:

• разработка backend-сервисов на Python;
• разработка и интеграцию REST API;
• интеграция различных LLM через API;
• разработка AI-агентов и агентных workflow;
• реализация Tool / Function Calling;
• работа с MCP и взаимодействием AI-агентов с внешними инструментами;
• разработка RAG-систем;
• построение ingestion и indexing pipeline;
• работа с embeddings, векторным, полнотекстовым и гибридным поиском;
• настройка reranking, query rewriting и других механизмов улучшения retrieval;
• разработка механизмов управления контекстом, состоянием и памятью AI-агентов;
• реализация обработки ошибок, timeout, retry и fallback-сценариев;
• тестирование и оценка качества AI-функциональности;
• настройка tracing, logging и metrics для AI-систем.

Что мы ожидаем

Backend

Необходим уверенный опыт работы с:

• Python;
• FastAPI;
• AsyncIO;
• REST API и backend-сервисами;
• PostgreSQL;
• Docker;
• Git.

LLM и AI-агенты

Важно понимать и уметь применять на практике:

• подходы к построению AI-агентов: Workflow, ReAct, Multi-Agent;
• работу с LLM API;
• Structured Output;
• Streaming;
• Tool / Function Calling;
• Prompt Engineering и Context Engineering;
• управление контекстом, состоянием и памятью агента;
• MCP;
• A2A;
• Human-in-the-loop;
• Guardrails;
• работу с различными LLM-моделями и провайдерами;
• tokenization, context window и ограничения LLM;
• обработку ошибок при работе с LLM и внешними tools: timeout, retry, fallback;
• компромиссы между качеством, latency и стоимостью использования моделей.

RAG и поиск

Ожидаем практический опыт построения RAG-систем и понимание следующих технологий и подходов:

• Embeddings;
• Semantic / Vector Search;
• BM25;
• Full-Text Search;
• Hybrid Search;
• Chunking Strategies;
• Metadata Filtering;
• Reranking;
• Query Rewriting / Expansion;
• Multi-Query Retrieval;
• Vector Databases — Qdrant или аналоги;
• построение ingestion / indexing pipeline;
• обновление и удаление документов из индекса;
• оценка качества retrieval и RAG.

AI Frameworks и SDK

Желателен опыт работы с:

• LangChain;
• LangGraph или аналогичными решениями;
• OpenAI SDK или SDK других LLM-провайдеров;
• MCP SDK;
• Qdrant SDK или аналогами.

При этом для нас важно не только знание конкретных библиотек, но и понимание общих принципов построения AI-систем без жесткой привязки к одному фреймворку.

Production и качество

Ожидаем понимание принципов эксплуатации AI-систем:

• tracing, logging и metrics;
• evals и benchmarking AI-агентов и RAG-систем;
• тестирование AI-функциональности;
• reliability при работе с LLM и внешними сервисами.

Что мы предлагаем

• Формат работы: дистанционно или в офисе (по желанию).
• График работы: проектная занятость.
• Карьерный рост: гарантируем поэтапное расширение задач и карьерное развитие с ростом заработной платы.
• Обучение и сертификация: за счет компании, график составляется с учетом пожеланий сотрудника.
• Дополнительные премиальные выплаты: за привод клиента в бизнес, за приглашение коллеги в компанию, и другие премии за эффективную работу.

Как мы заботимся о сотрудниках

• Материальная помощь по случаю рождения ребенка, свадьбы, утраты близкого
• Лаунж-зона для отдыха: оборудованная кухня, потрясающий кофе, настольные игры, турник, библиотека, кинотеатр
• Насыщенная корпоративная жизнь: путешествуем по России и не только, а также вместе ходим в театр, на квиз, на спортивные мероприятия и др.
• Корпоративный английский
• Компенсация коворкинга

Health can’t wait.

Not for symptoms to get worse. Not for a six‑month appointment. Not for a system to catch up. But that’s exactly how healthcare works today. You wait, until you can’t.

Alan exists to end the wait.

Health is a universal right, and we believe this right can only become real when it’s coupled with prevention. We need to stop treating health as something we repair and start treating it as something we build, every day. It’s not solely a question of willpower. It’s the healthcare system itself that needs to work for everyone, in a sustainable way.

So we are building the new standard in prevention insurance. Alan is the first company that integrates insurance, prevention, and care into a single, acclaimed user experience.

We are on an incredible journey to build a global leading company, with a unique culture. We already partner with 40K+ companies of all sizes, serving more than 1M+ members, and have reached €800M+ in ARR.

Prevention as the new norm. That's what we're building with our team of 1000+ people. If it speaks to you: we're hiring across France, Spain, Belgium, and Canada. And beyond.

⭐ The Engineering team ⭐

In our engineering team, we build the infrastructure, interfaces, and applications to provide first-class service to our members, health professionals, and even ourselves!

Being an engineer at Alan means joining a team of talented, committed and passionate engineers, with a lot of product interaction.

We move fast, with a lot of ownership, and are proud to tackle big problems!

Our process is very simple: those who make product decisions are the same ones who build them.

Want to know more? Read this article if you want to discover how life as an Engineer at Alan and this article on our Engineering career path.

🛠️ The Stack

Python/Flask, React, React Native, PostgreSQL in a monorepo. We deploy daily and believe in distributed ownership - you build it, you own it.

🤖 The Hopper crew

🎯 Mission:

• Hopper is Alan's internal agentic AI platform and every Alaner's AI companion: one unified productivity tool for coding, data, automation, research, and everyday work.

• It is a platform with a product on top. The product is the first and most demanding user of reusable components for agent orchestration, isolated execution, skills, connectors, permissions, audit, and evaluations.

It started as a coding agent. Watch how we built its first version and enabled anyone at Alan to ship code. Coding remains its most mature use case and the foundation we are expanding from.

🔭 Scope:

1. Product experience - durable AI sessions available from the web, Slack, Linear, and GitHub for coding, data analysis, automation, and general work

2. Agent runtime and orchestration - control plane, harness, model routing, long-running execution, recovery, and isolated sandboxes

3. Secure connectors - an MCP Gateway that manages identity, credentials, permissions, confirmations, sensitivity, and audit

4. Skills, automations, and artifacts - reusable workflows, scheduled or event-driven work, dashboards, and hosted tools

5. Trust and review - evaluations and product experiences that expose tests, screenshots, previews, queries, sources, and tool actions

👀 Focus for 2026:

Coding proved that Alaners want to delegate meaningful work to agents. Our 2026 focus is to make it the AI companion every Alaner can rely on: faster and more durable sessions, safe access to company tools and data, HDS-compatible infrastructure for sensitive workloads, stronger evaluations, and results people can inspect before acting on them.

👀 Focus for 2026:

In 2026, we're moving from "AI tools you monitor" to "AI agents you trust." That means scaling Hopper — Alan's own background coding agent — alongside the infrastructure that makes it reliable: managed agent pools, sandboxed environments, autonomous testing, and CI auto-fix. Engineers will routinely offload tasks to agents. Non-engineers will open pull requests after having easily tested their changes. Agents will validate their own work before it ships.

⭐ Is it you we’re looking for?

Experience we value

• 3+ years in full-stack software engineering roles

• Experience building products, internal platforms, frameworks, or infrastructure used by other people

• Depth in at least one relevant area: AI agents and evaluations, developer platforms, high-quality product UX, distributed systems and runtimes or security and authorization

• Ability to own work end to end, from a React interaction or API contract to reliability in production

• Experience with LLM APIs, agent harnesses, MCP, or AI-assisted coding tools is a strong plus

Mindset we value

• You think in terms of both product and platform experience: Alaners across engineering, product, data, sales, and operations are your customers

• You care about whether people can understand and verify what an AI system did

• You make concrete tradeoffs between speed, reliability, cost, security, and user experience

• You simplify complexity with clear abstractions and maintainable code

• You are collaborative, humble, and motivated by enabling others

• You are excited about AI changing who can build, investigate, and automate work

• You are fluent in English (no French required)

• Above all, we look for high potential and curiosity. Everything else is a bonus.

🌍 How we work

• Location: You must be legally eligible to work in France, Belgium, or Spain.

• Remote work: We offer remote work flexibility, but we value in-person collaboration

   

🎯 Important note: we hire people, not roles.

If you're excited about this opportunity but don't check every box, we'd love to hear from you. Everyone, no matter how underrepresented, should feel free to apply, as it can only bring learnings or success.

If you identify yourself as a woman: Did you know that research shows women often apply only when meeting 100% of requirements?

Remember, this is just a guide, not a checklist.

We'll be thrilled to receive your application!

To see all our opened Engineering positions, click here !

🔖 Check out our About Alan and Career pages, as well as our Medium, blog and Glassdoor page for more info.

You want to know more about Alan?

• 🙌 Perks & Benefits: Alaners are provided with a stimulating environment and perks ensuring they are happy, efficient and spend only high-quality time with co-workers.

• 🤘 A strong culture: People joining Alan are often surprised and delighted by our innovative working method. We have a set of cultural values that guide our approach to work

🔄 A quick note about the process

Note: While you're applying for a specific area, you may join a different engineering team based on where we think you'll have the most impact. Check out descriptions of other areas here.