Research Engineer - Search and Services
Mistral AI15 hours ago
Paris, France or London, United KingdomSenior
Responsibilities
- Design, build, and operate large-scale search infrastructure, including self-hosted Vespa clusters, managed indexes, and vendor search endpoints.
- Self-host and maintain structured data sources such as knowledge graphs, scholarly datasets, statistical databases, and open data portals.
- Design interfaces and tools that expose search and data services to models and agents through YQL, SPARQL, and MCP.
- Build ingestion, indexing, and serving pipelines for massive datasets and pretraining corpora.
- Partner with research, pretraining data, sandbox, and data platform teams to enable their workflows.
- Operate reliable, scalable, and fast services on infrastructure with hundreds of terabytes of NVMe storage and thousands of CPU cores.
- Produce documentation and other content that helps teams use the services effectively.
Requirements
- 5+ years of successful experience in search engineering, data infrastructure, or a similar SRE/platform role.
- Proficiency in software development with Python, Go, or similar languages.
- Hands-on experience with large-scale search or data systems such as Vespa, Elasticsearch, OpenSearch, or ClickHouse.
- Exposure to site reliability practices including root cause analysis, in-production troubleshooting, and on-call rotations.
- Exposure to infrastructure management, including containerization, Kubernetes, infrastructure-as-code, monitoring, logging, alerting, and observability.
- Experience designing and operating data pipelines that process large amounts of data.
- Strong problem-solving and communication skills, including risk assessment and gaining stakeholder buy-in.
- Preferred experience with Vespa or equivalent information retrieval systems, MCP servers or LLM tool-serving infrastructure, knowledge graphs, RDF, SPARQL, PostgreSQL, ClickHouse, DuckDB, bare-metal infrastructure, or HPC environments.
Benefits
- Benefits may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal allowances, transportation allowances, and other location-specific perks.
- Benefits vary by country and applicants should refer to the company’s Benefits page for current location-specific details.
Tech Stack
Categories
BackendData Engineering
About Mistral AI
Mistral AI builds foundation language models and full‑stack AI solutions for enterprises, offering APIs, on‑prem deployment, developer tools, and applications. The privately held company, founded in 2023 and headquartered in Paris, partners with organizations in finance, manufacturing, defense, healthcare, and the public sector to co‑create customized systems. It releases open‑source models alongside commercial offerings and makes its models available through major cloud marketplaces.