- Location
- Warsaw
- Workplace
- Hybrid
- Type
- Full-time
- Department
- Engineering & Infra
- Source
- Lever
Description
About Mistral
At Mistral AI, we believe in the power of AI to simplify tasks, save time and enhance learning and creativity. Our technology is designed to integrate seamlessly into daily working life.
We democratize AI through high-performance, optimized, open-source and cutting-edge models, products and solutions. Our comprehensive AI platform is designed to meet enterprise needs, whether on-premises or in cloud environments. Our offerings include le Chat, the AI assistant for life and work.
We are a dynamic, collaborative team passionate about AI and its potential to transform society.
Our diverse workforce thrives in competitive environments and is committed to driving innovation. We are creative, low-ego and team-spirited.
Join us to be part of a pioneering company shaping the future of AI. Together, we can make a meaningful impact. See more about our culture on https://mistral.ai/careers.
Role summary
We are seeking passionate and skilled software engineers to join our Warsaw-based Context Engine team to build and enhance Mistral’s agent harness, enabling us to deliver production-grade knowledge processing, directly impacting how users interact with our AI platform.You’ll work on building reliable, high-performance backend systems and APIs that serve millions of users and developers. Your work will directly impact the developer and user experience, making it more engaging, efficient, and intuitive. We welcome engineers from mid - senior to staff level who are eager to learn, collaborate and ship impactful products.
What you will do
Depending on your skills and field of expertise, you will be involved in key components of our technology, including:
Backend Development
- Design, develop and maintain scalable, robust backend features and APIs using modern frameworks.
- Ensure high performance and reliability across our distributed systems.
System Architecture
- Design and implement efficient, secure and scalable architectures that support our fast-growing products.
- Collaborate with infrastructure teams on deployment, monitoring, and performance optimization.
Code Quality
- Write clean, maintainable and well-documented code.
- Participate in code reviews and contribute to technical standards and best practices.
Cross-functional Collaboration
- Work closely with product managers, front-end engineers, designers and data/AI engineers to deliver end-to-end features.
- Partner with teams across harness SDK team, the enterprise connectors (MCP platform) team, and search infrastructure (Vespa-based) while building and enhancing Mistral’s agent harness (Vibe/Le Chat work mode) to enable models to navigate complex enterprise knowledge graphs.
Problem-Solving & Innovation
- Tackle complex engineering challenges, from distributed systems to AI product integration.
- Stay up-to-date with new technologies (e.g., AI/LLM integration, observability, or backend frameworks) and bring them into production when relevant.
About you
• Degree in Computer Science, Software Engineering, or equivalent practical experience.
• Proficiency in Python or another backend language (JavaScript/TypeScript, C#, Golang). Engineers are assessed in their preferred language during a live coding session.
• Strong understanding of backend fundamentals: APIs, databases, caching, messaging systems and distributed architectures.
• Strong problem-solving abilities and attention to detail.
• Ownership mindset capable of shipping end-to-end features with minimal oversight.
• Excellent communication skills and collaborative attitude.
• Team-oriented, low-ego mindset and curiosity for learning.
Now, it would be ideal if you had experience with:
• Front-end development (Typescript, React, NextJS...) or full-stack exposure
• Infrastructure management (Docker, CI/CD, Kubernetes, Helm, Terraform...)
• AI/ML engineering
• Observability and monitoring tools (Prometheus, Grafana, Datadog…).
• UX and product-centric mindset.
Hiring Process
• Introduction call - 45 min
• Live-coding interview - 45 min
• System Design interview - 45 min
• Hiring Manager interview - 30 min
• Deep Dive Interview (only for leads & staff engineers) - 60 min
• Culture-fit discussion - 30 min
• Reference checks
Our Culture
We're driven to build a strong company culture and are looking for individuals with solid alignment with the following:
• Reason with rigor
• Are you audacious enough?
• Make our customers succeed
• Ship early and accelerate
• Leave your ego aside
Engineering blog
Our first Engineering blog post is live, you can check it out here !
Skills
PythonJavaScriptTypeScriptReactDockerKubernetesTerraformCI/CDGo
