La descripción de esta empresa todavía no está disponible en este idioma.
Software Engineer, Core Infrastructure
Construirás la infraestructura de computación que permite a los equipos de investigación y a los socios ejecutar modelos en GPU. El puesto abarca la optimización de la inferencia, los sistemas distribuidos y la experiencia de desarrollo en AWS y Google Cloud. Tienes al menos cuatro años de experiencia en sistemas distribuidos o infraestructura de producción.
3× más posibilidades de conseguir una entrevista con un email en frío
Ver la oferta originalDatos sobre Boltz
- Sector
- Salud, farmacia y biotecnología
- Última ronda
- Série A · 2026-11-01
- Importe anunciado
- 110 000 000 $
- Ofertas abiertas
- 12
Inversores mencionados
Detalles de la oferta
La descripción completa publicada por Boltz.
About boltz
Boltz is a public benefit company building the next generation of AI-powered molecular modeling tools to make biology programmable and accelerate drug discovery, while keeping frontier capabilities broadly accessible. Boltz was founded by former MIT scientists who created Boltz-1, the first fully commercially available open-source model to approach AlphaFold 3-level accuracy in predicting the 3D structure of biomolecular complexes. We focus on two things: - Foundation models.
Our open models, Boltz-1, Boltz-2 and BoltzGen, are trusted by 100,000+ scientists across biotech and academia, and used in programs at every Top 20 pharma as well as leading agrichemical and industrial research organizations. Our latest proprietary foundation models power our products and the custom models we build with partners. - Boltz Lab and the Boltz API. Our products run our latest models, design pipelines (BoltzMol for small molecules, BoltzProt for protein design) and agents as reliable, production-grade tools built around real chemistry and biology workflows.
Teams start from a target and a hypothesis, then generate, evaluate, and rank candidate molecules in Boltz Lab, run our models from their own code and agents through the Boltz API, or deploy them inside their own environment. The two feed each other: our open releases earn scientific credibility and community insight, and our products turn our full range of models into real impact for partners including Pfizer, Takeda, GSK, Bristol Myers Squibb and DSM-Firmenich. You can read more about our mission, research and product vision in our manifesto https://boltz.bio/manifesto.
About the role
Every model Boltz trains, every design campaign a partner runs and every prediction served through Boltz Lab and the Boltz API runs on the compute platform this team builds. How fast our researchers move, and how much each GPU-hour delivers for our partners, comes down to it. The team has a dual mandate: serve our models to partners as fast, cheaply and reliably as possible, and give our researchers infrastructure that turns an idea into a running GPU job in minutes. You will go deep in one of three areas and stay fluent in the other two.
We match your focus after the interviews, based on your interests and what the team needs most.
What you'll do
Inference performance: make our models faster and cheaper to serve across GPU types and clouds. Profile end to end, place work by memory and hardware, batch and scale intelligently, and treat correct outputs as part of performance. - Distributed systems and compute: run a multi-cloud GPU fleet on AWS and Google Cloud. Scheduling, autoscaling, reserved and spot capacity, recovery from node failures, storage and data access, observability, and knowing what every GPU-hour costs. - Developer experience: own how engineers and researchers build, test and ship.
One monorepo with sub-minute CI is an insane productivity multiplier, and you keep it that way as the team and codebase grow: dev environments, builds and remote execution, and the path from a laptop to thousands of GPUs. This role is not an ML research role. You won't design model architectures, but you will make every model we build run better.
About you
MINIMUM
Requirements
4+ years building and operating distributed systems or infrastructure in production.
- Deep engineering fundamentals: you understand what happens below the abstractions you use (operating systems, networking, memory, concurrency), and you can read and improve large codebases you didn't write.
- Production Kubernetes and infrastructure-as-code on AWS and/or Google Cloud.
- Real depth in at least one area: inference or GPU performance, distributed compute, or developer experience (builds, CI, environments).
- You own what you ship: on-call, postmortems, and fixing the root cause.
- Pragmatic and low ego; you pick up whatever needs doing and want to learn ML systems.
Preferred requirements
GPU performance concepts (memory bandwidth, VRAM, batching, NCCL). Being able to reason about them matters more than having written kernels.
- Ray, Modal or Kueue, and the ideas behind them: tasks and actors, serverless GPU functions, gang scheduling, quotas, fair sharing and preemption.
- Bazel or other large monorepo build and CI systems.
- Observability from the fleet down to a single process: OpenTelemetry, continuous profiling with tools like Parca, and low-level tracing with ptrace or eBPF.
- Scientific or numerical computing workloads. We know great people don't always tick every box. If this role excites you and you meet most of the essentials, we'd like to hear from you.
What we offer
Opportunity to drive outsized real-world impact by building tools that empower thousands of scientists across the industry.
- Work alongside one of the most talent-dense teams in the field.
- Significant ownership and independence, with responsibility for driving projects from concept to deployment.
- Highly competitive salary with meaningful equity in a public benefit company. -
Benefits
- 25 days annual leave plus bank holidays
- Annual team offsite trip
- Private healthcare (BUPA); covering pre-existing conditions
- Pension program
- Paid parental leave
- Wellhub gym membership
- Free lunch everyday
- Travel expenses HOW WE HIRE
- Initial screen with a member of the Talent team
- Technical / take-home / presentation interview
- Onsite in London [or virtual onsite] with the team
- Offer + Onboarding OUR COMMITMENT Boltz is committed to building a diverse team and an inclusive workplace. We welcome applicants of all backgrounds. If you need any adjustments during the hiring process, tell us and we'll make it work.
Requisitos
- Al menos 4 años construyendo y operando sistemas distribuidos o infraestructura en producción
- Sólidos fundamentos de ingeniería en sistemas operativos, redes, memoria y concurrencia
- Kubernetes en producción e infraestructura como código en AWS y/o Google Cloud
- Experiencia profunda en inferencia o rendimiento de GPU, computación distribuida o experiencia de desarrollo
Ventajas mencionadas
- 25 días de vacaciones anuales más festivos
- Viaje anual del equipo
- Seguro médico privado (BUPA), con cobertura de enfermedades preexistentes
- Plan de pensiones
- Permiso parental remunerado
- Membresía de gimnasio Wellhub
- Almuerzo gratis todos los días
- Gastos de viaje
Inscribirme en esta oferta
¿Cómo inscribirme?
La oferta está publicada en el sitio de Boltz. Abre la oferta original ↗ para enviar tu candidatura. Screeningpass no rellena formularios por ti.
¿A quién escribir en Boltz para este puesto?
Inicia una búsqueda de contacto desde esta página. Screeningpass te propone hasta tres personas vinculadas al puesto. Tú eliges a quién escribir y Screeningpass busca su correo profesional y prepara un mensaje. Lo revisas y lo envías tú con Gmail. No siempre hay una dirección de correo disponible y nunca se garantiza una respuesta.
¿Cuánto cuesta buscar un contacto?
Una búsqueda cuesta 1 crédito. Se te devuelve si la búsqueda falla. Al registrarte recibes 3 créditos, para hacer 3 búsquedas.
¿Para qué sirve Screeningpass?
Screeningpass reúne ofertas de prácticas y empleo publicadas por las empresas. Para una oferta, Screeningpass encuentra una persona con la que contactar en la empresa, busca su correo profesional y prepara un mensaje a partir de tu CV. Ver el funcionamiento en detalle.