SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Mistral is seeking a Research Engineer to join the newly forming Search and Services Platform team within Research Platform. This role focuses on building and operating large-scale search and services infrastructure that powers Mistral's AI models and agents.
Key Responsibilities:
- Design, build, and operate large-scale search infrastructure, including self-hosted Vespa clusters indexing web-scale corpora, managed indexes for smaller datasets, and vendor search endpoints.
- Self-host and maintain structured data sources such as knowledge graphs (Wikidata, UniProt, Materials Project), scholarly data (OpenAlex, OpenAIRE), statistical databases (Eurostat, World Bank, IMF, OECD), and open data portals.
- Design interfaces and tools to expose services to models and agents, including direct YQL or SPARQL queries and refined MCPs to mimic external services, supporting data generation and agentic training.
- Build data pipelines that ingest, index, and serve massive datasets, including indexing pretraining corpora for exploration, deduplication, and eval-leakage checks.
- Collaborate closely with researchers and adjacent teams (pretraining data, sandbox, data platform) to understand workflows and enable them to leverage your expertise.
- Communicate and produce documentation to help teams maximize the value of the services you build.
The role operates at scale: infrastructure measured in hundreds of terabytes of NVMe storage and thousands of CPU cores supporting both data generation and critical training runs. You will work in a distributed, collaborative environment across Europe, North America, Asia, and the Middle East.
Requirements:
- 5+ years of successful experience in search engineering, data infrastructure, or similar SRE/platform roles.
- Proficiency in software development (Python, Go, or similar) and programming best practices.
- Hands-on experience with large-scale search or data systems (e.g., Vespa, Elasticsearch/OpenSearch, ClickHouse, or similar).
- Exposure to site reliability engineering: root cause analysis, in-production troubleshooting, on-call rotations.
- Exposure to infrastructure management: containerization, orchestration (Kubernetes), infra-as-code, monitoring, logging, alerting, observability.
- Experience designing and operating data pipelines that handle large amounts of data.
- Excellent problem-solving and communication skills; ability to contextualize, gauge risks, and secure buy-in for high-stakes solutions.
- Ownership mindset, high agency, and commitment to continuous learning and improvement.
- Autonomous, self-driven, and able to thrive in a fast-paced startup environment.
- Team-oriented with low ego.
Preferred Qualifications:
- First-hand Vespa (or equivalent large-scale information retrieval) experience.
- Experience building or operating MCP servers/tool-serving infrastructure for LLMs.
- Familiarity with knowledge graphs, RDF/SPARQL, or large structured databases (PostgreSQL, ClickHouse, DuckDB).
- Experience with large bare-metal infrastructure or HPC environments.
