Publié il y a 1 heure
Software eng, inference
@ turbopuffer
Canada
En bref
turbopuffer is hiring a software engineer to build inference for search over more than a trillion documents. The role works closely with inference providers to keep p99 latency low, improves how the database talks to them, and integrates new embedding and reranking models. It is a full-time position.
Responsabilités :
- Keep p99 inference latency low with inference providers
- Improve database interaction with inference providers
- Integrate new embedding and reranking models
- Automate own role over time
Résumé des exigences :
- Systems language experience (Rust, C++, Java, Go)
- Production inference deployment experience
- Experience with large dataset processing
- Understanding of latency-throughput tradeoffs
- Familiarity with vLLM and SGLang
- Clear writing and honest communication
Outils et compétences
Source et dates
Site carrière / système de candidatures · ashby
- Date publiée par l’employeur
- 2026-11-16
- Première détection par notre source
- 2026-11-16
- Mise à jour du dossier source
- 2026-11-16
Ces dates décrivent le dossier source, pas une vérification en direct du recrutement. Consultez l’offre originale.
Détails du poste
| Domaine | Développement logiciel |
| Heures par semaine | 40 (estimé) |
| Milieu de travail | Bureau |
| Position | Surtout assis |
| Exigences physiques | physique faible · ordinateur élevé |
Résumé et détails rédigés par l’IA à partir de l’offre; l’offre de l’employeur fait foi.
turbopuffer
Profil d’entreprise sauvegardé
Renseignements historiques provenant d’un profil The Jobs API sauvegardé (champs LinkedIn/Crunchbase). Ils ne sont pas vérifiés en temps réel; les chiffres peuvent avoir changé. Les valeurs manquantes restent inconnues.
serverless {vector, full-text} search from first principles on object storage. faster, 10x cheaper, extremely scalable
Description complète de l’entreprise
turbopuffer is a fast search engine that combines vector and full-text search using object storage, making all your data easily searchable. Using only object storage for state and NVMe SSD with memory cache for compute, turbopuffer scales horizontally to handle billions of documents. The system caches only actively searched data while keeping the rest in low-cost object storage, offering competitive pricing. Cold queries process 1 million vectors in 500ms (p90), while warm queries take just 20ms (p50). This architecture means it's as fast as in-memory search engines when cached, but far cheaper to run. Storing data in cache and object storage costs less than traditional replicated disk systems, even for frequently accessed data.
- Abonnés LinkedIn
- 7 114
- Personnes associées sur LinkedIn
- 37
- Catégories d’activité
- Information Technology
- Database
- Autres noms enregistrés
- turbopuffer
- Le profil indique une agence de recrutement
- Non
- Investissement total déclaré
- 0
La devise et la date d’observation ne sont pas fournies; ce n’est ni une valorisation actuelle ni une ronde de financement.
turbopuffer is a fast search engine that combines vector and full-text search using object storage, making all your data easily searchable. Using only object storage for state and NVMe SSD with memory cache for compute, turbopuffer scales horizontally to handle billions of documents. The system caches only actively searched data while keeping the rest in low-cost object storage, offering competitive pricing. Cold…
| Champ | Valeur |
|---|---|
| Secteur | Technology, Information and Internet |
| Taille | 11-50 employees |
| Type d’organisation | Privately Held |
| Fondée en | 2023 |
| Offres sur Jobsy | 6 |
| Voir la page |
turbopuffer is looking for a software engineer who wants to build inference for searching +1T documents.
what you'll do:
work closely with our inference providers to make sure that the p99 inference latency stays as low as possible
write code to improve how the database interacts with our inference providers
integrate new embedding & reranking models into turbopuffer
automate yourself out of a job
must have:
engineering
you've worked in a systems language (Rust, C++, Java, Go, etc.)
experience in inference engineering, e.g. managing a production deployment of an LLM/embedding/reranking model
worked on handling/processing large datasets
you love shipping things to prod
domain expertise
you understand the tradeoff between latency and throughput for model deployments and you know how to think about improving model performance
keeping up with state-of-the-art embedding & reranker models and their evaluation
you’re familiar with the most common inference engines like vLLM and SGLang
you know how to manage the infra of model deployments and how to reason about GPU autoscaling.
typist - you can write well and can explain complex ideas simply
human - you build trust and admit what you don’t know
nice to have:
an interest in embedding & reranker model training
prior experience in vector and full-text search
knowledge about in-depth areas of inference engines & GPU engineering
tpuf is hardcore & whimsical. we value:
overstep > understep
show > tell
complexity is earned
showing up as part of our customer’s team
making stuff easy to react to
Journal
Visible seulement par vous. Conservé sur cet appareil, et dans votre compte une fois connecté.