Who are we?
Founded in 2012, Take a Chef was born from the belief that exceptional culinary experiences should be accessible beyond traditional restaurant settings. We envisioned a world where top-tier chefs could bring their talents directly to the dining tables of discerning individuals and families. ️
Combining cutting-edge technology with a deep passion for food and hospitality, we've become the leading global platform for high-quality private chef services.
Last year, we served over 500,000 clients in more than 100+ countries, working with a network of 70,000+ private chefs and partnering with renowned luxury travel brands like Airbnb, Onefinestay, Le Collectionist
About the role
At Take a Chef, we are looking for an AI Software Engineer to program, deploy, and maintain these end-to-end services. Someone who is comfortable writing microservices in FastAPI / Django, integrating LLMs and real data pipelines, orchestrating multi-step intelligent agents, packaging everything in Docker, and getting it ready for production in cloud / on-prem.
Requirements
• Academic Background: Degree in Computer Engineering, Software Engineering, Computer Science or Physics / Mathematics with real experience in backend development.
• Years of experience: 1-2 years developing software in Python in real environments.
Technical Knowledge
️ Backend in Python
• FastAPI (routers, dependencies, Pydantic validation).
• Django / Django REST Framework is a plus.
• Design of clean and documented REST APIs.
Infra and deployment
• Docker (Dockerfile, docker-compose, secure environment variables).
• Preparing services for production: structured logging, error control, timeouts, token/API key authentication.
• Work with PostgreSQL or other relational databases.
Generative AI, RAG and Agents
• Use of LLMs (OpenAI / Azure OpenAI / Bedrock / open source models served locally).
• Understanding real limits of an LLM: cost per token, latency, context.
• Knowledge of prompting, embeddings and frameworks like LangChain or LlamaIndex.
• Design and implementation of **orchestrated agents/autonomous systems** (for example with LangChain, LangGraph, AutoGen or similar architectures), including tool calling, step-by-step reasoning and coordination between specialized agents.
• Knowledge of RAG architectures: Embeddings, semantic retrieval, grounding, interaction with vector databases (Qdrant, Milvus, FAISS, Pinecone...).
️ Knowledge of machine learning frameworks and libraries
• Experience in using data science libraries (TensorFlow, PyTorch, pandas, NumPy, scikit-learn).
Work Methodologies
Fast iteration work, frequent releases, product mindset.
Direct collaboration with the Head of AI and other business/tech teams.
Familiarity with agile practices (Scrum / Kanban).
Personal Skills
Structured thinking and technical judgment.
Ability to solve complex problems and analytical thinking.
Effective communication skills to collaborate with multidisciplinary teams.
Valued
Basic experience with AWS (ECS Fargate, RDS Postgres, S3) or on-prem with containers.
Observability / metrics (OpenTelemetry, Prometheus, CloudWatch, etc.).
CI/CD (GitHub Actions, Bitbucket Pipelines).
Fundamentals of evaluation: knowing how to measure if the system really improves (accuracy, factuality, cost).
Why choose us?
Positive Work Environment – A collaborative, innovative culture that values well-being and team spirit.
Work-Life Balance – Flexibility and support so you can grow personally and professionally.
Employee Development – Access to training and workshops to expand your skills.
Competitive Compensation – Attractive salary plus annual performance bonuses.
Paid Time Off – 25 vacation days per year to recharge.