B
boltzvia muse
Senior Machine Learning Engineer, GPU Optimization
London, ENG, GBPosted 3d ago
ML EngineerSeniorFull-time
About the Role
**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 began as an MIT spin\-out. Our founders built Boltz\-1 at MIT, and it became the first fully open\-source model to match AlphaFold 3's accuracy in predicting the 3D structure of biomolecular complexes.
We focus on two things:
* **Open foundation models.** Boltz\-1, Boltz\-2, and BoltzGen are open models 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.
* **Boltz Lab.** Our commercial platform runs our latest models and design 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, while we provide the compute, infrastructure, and collaboration layer so their scientists can move faster.
The two feed each other: open\-source adoption earns scientific credibility and community insight, and Boltz Lab turns that into real impact on our partners' discovery programs.
You can read more about our mission, research and product vision in our manifesto.
**About the role**
As a ML Engineer in GPU Optimization, you will own how fast and how reliably our structure models train. Every hour cut from a training run is another experiment our researchers can run; a near\-term goal is a 1\.5x speedup on our structure model, with long runs finishing without interruption.
You will spend most of your time embedded with a research team (such as pre\-training, post\-training or biologics), working side by side with research scientists, and the rest with Research Engineering on tools shared across teams. You'll also work with Platform Engineering, who own GPU orchestration across Boltz.
This role is ideal for an engineer who loves profiling, can look at a GPU utilization or loss curve and know where to start digging, and wants their speedups to show up in better science.
**What you'll do**
* Speed up large\-scale training of our structure models, finding and removing bottlenecks in kernels, memory, communication, data loading and parallelism.
* Write and tune custom GPU kernels where they pay off (e.g. Triton or CUDA), and get the most from each new GPU generation.
* Make long training runs complete without interruption: diagnose failures and degraded runs from throughput, utilization and loss signals, and fix the root cause.
* Build reusable profiling and optimization tooling, including agent\-assisted, profile\-guided optimization, so speedups carry across teams.
* Feed what you learn about performance back into how researchers design models and experiments.
**About you**
### **Minimum Requirements**
* Experience in optimizing deep learning training on multi\-node GPU clusters (e.g. FSDP, DeepSpeed, Megatron).
* Deep GPU performance expertise: profiling (e.g. PyTorch Profiler, Nsight), memory and communication tuning, and kernel work in Triton or CUDA.
* Strong PyTorch and Python, with enough ML intuition to judge how an engineering change affects training dynamics and results.
* A track record of measurable speedups or reliability gains on real, large training workloads.
* You enjoy investigating problems with researchers, rather than taking tickets.
### **Preferred Requirements**
* Exposure to structure prediction, diffusion models, or biology and chemistry data.
* Experience with Kubernetes and cluster operations; coding agents as a core part of your workflow.
* Experience using Boltz models, or contributions to open\-source training frameworks or kernel libraries.
We know great people don't always tick every box. If this role excites you and you meet most of the minimum requirements, we'd like to hear from you.
**What we off
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 began as an MIT spin\-out. Our founders built Boltz\-1 at MIT, and it became the first fully open\-source model to match AlphaFold 3's accuracy in predicting the 3D structure of biomolecular complexes.
We focus on two things:
* **Open foundation models.** Boltz\-1, Boltz\-2, and BoltzGen are open models 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.
* **Boltz Lab.** Our commercial platform runs our latest models and design 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, while we provide the compute, infrastructure, and collaboration layer so their scientists can move faster.
The two feed each other: open\-source adoption earns scientific credibility and community insight, and Boltz Lab turns that into real impact on our partners' discovery programs.
You can read more about our mission, research and product vision in our manifesto.
**About the role**
As a ML Engineer in GPU Optimization, you will own how fast and how reliably our structure models train. Every hour cut from a training run is another experiment our researchers can run; a near\-term goal is a 1\.5x speedup on our structure model, with long runs finishing without interruption.
You will spend most of your time embedded with a research team (such as pre\-training, post\-training or biologics), working side by side with research scientists, and the rest with Research Engineering on tools shared across teams. You'll also work with Platform Engineering, who own GPU orchestration across Boltz.
This role is ideal for an engineer who loves profiling, can look at a GPU utilization or loss curve and know where to start digging, and wants their speedups to show up in better science.
**What you'll do**
* Speed up large\-scale training of our structure models, finding and removing bottlenecks in kernels, memory, communication, data loading and parallelism.
* Write and tune custom GPU kernels where they pay off (e.g. Triton or CUDA), and get the most from each new GPU generation.
* Make long training runs complete without interruption: diagnose failures and degraded runs from throughput, utilization and loss signals, and fix the root cause.
* Build reusable profiling and optimization tooling, including agent\-assisted, profile\-guided optimization, so speedups carry across teams.
* Feed what you learn about performance back into how researchers design models and experiments.
**About you**
### **Minimum Requirements**
* Experience in optimizing deep learning training on multi\-node GPU clusters (e.g. FSDP, DeepSpeed, Megatron).
* Deep GPU performance expertise: profiling (e.g. PyTorch Profiler, Nsight), memory and communication tuning, and kernel work in Triton or CUDA.
* Strong PyTorch and Python, with enough ML intuition to judge how an engineering change affects training dynamics and results.
* A track record of measurable speedups or reliability gains on real, large training workloads.
* You enjoy investigating problems with researchers, rather than taking tickets.
### **Preferred Requirements**
* Exposure to structure prediction, diffusion models, or biology and chemistry data.
* Experience with Kubernetes and cluster operations; coding agents as a core part of your workflow.
* Experience using Boltz models, or contributions to open\-source training frameworks or kernel libraries.
We know great people don't always tick every box. If this role excites you and you meet most of the minimum requirements, we'd like to hear from you.
**What we off
Similar Jobs
C
Capital One• 1mo ago
Machine Learning Engineer 4 (IC)
McLean, VAFull-time
W
Waystone• 6mo ago
AI Engineer
Leeds, West YorkshireFull-time
A
Aderant• 1mo ago
AI Engineer – Center of Excellence
Atlanta, GAFull-time
S
Signifyd• 1mo ago
Senior Machine Learning Engineer I // II
Chicago, ILFull-time