2,461,807open jobs
149,882companies
317,954added this week
Browse all
Location
In office (San Francisco)
Employment
Full-Time

Confirmed on the employer's own hiring board on Nov 22, 2026. First seen by Alion on Nov 12, 2026.

Overview
Company
Impact
Profile match
We train models for cybersecurity and build the tools to put them to work.

Job description

Collision AI is building models and agents for cyber defense. You’ll develop the infrastructure that trains them through reinforcement learning, helping researchers move from initial experiments to efficient, reliable runs across many GPUs.

The role combines systems engineering with a practical understanding of RL. Infrastructure problems can change learning behavior: delayed weight updates, differences between trainer and inference log probabilities, or off-policy drift can resemble problems with the training method itself. You’ll work closely with researchers to understand these interactions and improve performance without compromising training correctness.

What you’ll work on

  • Training and rollout systems. Coordinate trainers, rollout workers, environment execution, and reward computation across GPU clusters. Integrate SGLang for high-throughput sampling, improve trainer-to-inference weight synchronization, and support asynchronous rollouts and off-policy training.

  • Performance at scale. Improve distributed training through FSDP, tensor and pipeline parallelism, and efficient NCCL communication. Profile bottlenecks across compute, memory, and networking, and make targeted runtime or CUDA/Triton kernel improvements where they meaningfully improve training efficiency.

  • Training correctness and reliability. Develop monitoring and diagnostics that catch stale weights, trainer-inference log-probability mismatches, and off-policy drift during long runs. Build reproducible debugging workflows and recovery mechanisms, and use controlled comparisons to understand how infrastructure changes affect learning.

Required qualifications

  • Strong Python and PyTorch skills, with experience building distributed training or inference infrastructure.

  • Practical understanding of LLM reinforcement learning, including rollout policies, reward computation, and policy updates.

  • Experience profiling GPU workloads and resolving performance, correctness, or reliability issues in complex ML systems.

  • Ability to investigate problems across research and infrastructure code and validate changes on real training runs.

Bonus qualifications

  • Experience developing RL training pipelines, particularly asynchronous or off-policy systems.

  • Work on agent environments, sandboxed execution, reward models, or verification pipelines.

  • Experience extending SGLang, vLLM, or comparable inference runtimes.

  • Experience with FSDP, tensor or pipeline parallelism, NCCL, CUDA, or Triton.

Free account
Stop reading job ads. Get the ones that fit.
One free account turns this page into a shortlist built around your stack, your level and your pay.
Match on every job. Stack, seniority, pay and location, scored against your profile.
2,461,807 open roles. Read straight off company career pages, refreshed every day.
Unlimited applications. Every one you send is tracked in one place, on-site or on a company board.
3 tailored CVs a month. Rewritten for the exact job you are applying to. Included free.
Create a free account Continue with Google
Free forever. No card. Under a minute.

Your match

How well do you fit this role?
Two answers are enough for a real match. No account needed.
Check my fit
Answers stay in this browser until you create an account.

Recommended for you based on this role

DevOps
Remote, many countries
Similar stack
Same company
San Francisco
$144k – $194k per year · Equity · In office · Full-Time · 3+ years exp · Bachelor's Degree · Seattle
Java
C#
C++
Perl
AI/ML
AI Agents
LLM
DevOps
AWS
Apply
$108k – $171k per year · In office · Full-Time · Cambridge
Python
SQL
Databases
PostgreSQL
DevOps
Rest API
AWS
Life Sciences
Cell Culture
LIMS
Benchling
Apply
$168k – $360k per year · In office · Full-Time · Fremont
Python
SQL
Databases
MySQL
PostgreSQL
DevOps
Rest API
Splunk
Prometheus
Grafana
Alertmanager
Linux
BGP
Apply
$200k – $250k per year · In office · TS/SCI · Full-Time · Aurora
DevOps
Windows
Apply
$12k – $21k per year · Remote (EAEU) · Full-Time · Almaty
DevOps
Cloudflare
Linux
DNS
Apply
Remote (Europe)
Python
Ruby
Bash
Ruby
Sidekiq
Databases
PostgreSQL
Redis
DevOps
Terraform
GCP
GitHub Actions
OpenTelemetry
Datadog
Prometheus
Azure
CI/CD
AWS
Kubernetes
Grafana
Amazon EKS
AWS Fargate
AWS Lambda
SLI/SLO/SLA
IAM
Amazon ECS
Linux
Cybersecurity
Snyk
Wiz
Apply
Remote (EAEU) · Full-Time · 1+ year exp · Bachelor's Degree · Moscow
SQL
Bash
Databases
PostgreSQL
RabbitMQ
Apache Kafka
DevOps
Docker Compose
CI/CD
Docker
Linux
Management
Jira
YouTrack
QA
Swagger
Apply
DevOps Engineer 1 day ago
$66k – $82k per year (net) · Remote (EU, United Kingdom, Switzerland, Iceland) · Full-Time · Tallinn
Databases
Apache Kafka
DevOps
Terraform
Istio
Terragrunt
CI/CD
GitOps
ArgoCD
Jenkins
AWS
Docker
Kubernetes
Cloudflare
Platform Engineering
Service Mesh
Amazon EKS
GitLab
IAM
Linux
DNS
Apply
Remote (Switzerland) · Full-Time · Bachelor's Degree · Zurich · Brussels · Barcelona · Bratislava · London
DevOps
Cilium
GitOps
Kubernetes
eBPF
BGP
Apply
DevOps Tech Lead 1 day ago
In office · 7+ years exp · San Francisco
Python
Go
Bash
DevOps
Terraform
GCP
GitHub Actions
Loki
PagerDuty
Prometheus
Pulumi
GitLab CI
Azure
CI/CD
AWS
Docker
Kubernetes
Grafana
Chaos Engineering
SLI/SLO/SLA
GitHub
GitLab
Linux
Web3
Solana
Chainlink
Cosmos
Staking
MEV
Jito
Cosmos SDK
Pyth
Apply
≈ $180k – $399k per year (Estimated) · In office · Bachelor's Degree · San Francisco
Python
C#
C++
DevOps
CI/CD
Git
Apply
$440k – $500k per year · In office · 10+ years exp · New York · San Francisco
Apply
$240k per year · Equity 0.5–2% · In office · Full-Time · 3+ years exp · San Francisco
Go
Rust
TypeScript
Databases
PostgreSQL
AI/ML
Model Context Protocol
AI Agents
Multi-Agent Systems
DevOps
Docker
Kubernetes
Linux
Apply
$127k – $159k per year · Hybrid · 6+ years exp · Bachelor's Degree · San Francisco
Design
AutoCAD
Apply
See all jobs
This is one of many
2,461,807 more open roles from verified company boards, updated every day.