Senior AI Infrastructure Engineer (MLOps / Model Serving)
Compensation estimateAI
See base, equity, bonus, and total comp estimates for this role — free, no credit card.
Sign up to see compensation estimateSenior AI Infrastructure Engineer (MLOps / Model Serving)
Location:
*Montreal or Remote*
Nura Studios is building a new generation of AI-powered creative tools for storytelling.
We are developing a platform that enables creators to produce cinematic-quality episodic content — from concept and script all the way to animation and final edit — within a single integrated environment. Our platform combines Generative AI, real-time graphics, and scalable cloud infrastructure to remove the traditional barriers to high-end content production. At the center of this platform is
Showcraft
, Nura’s creation environment that guides creators through the entire storytelling process — from idea to final frame.
Our founding team has decades of experience building creative technologies used by millions of creators across companies such as
Unity, Adobe, Roblox, and Disney
.
We are a small, highly technical team of engineers, artists, and researchers building the future of AI-driven storytelling.
About the Role
We are looking for a
Senior AI Infrastructure Engineer
to help build and operate the platform that powers large-scale Generative AI workloads
.
This role focuses on:
- MLOps and model serving
- Distributed GPU infrastructure
- Large-scale AI inference systems
You will work on systems that deploy and scale AI models used for:
- Image generation and editing
- Video synthesis
- Embeddings
- 3D world synthesis and understanding
- Multimodal creative AI workflows
You will help design and operate our
state-of-the-art inference platform
, running large-scale workloads across multiple GPU cloud providers while ensuring
performance, reliability, observability, and cost efficiency
.
You don’t need to match every requirement below. We value
curiosity, pragmatism, and the ability to ship production systems.
What You’ll Work On
*AI Infrastructure & Model Serving*
- Build systems for
serving large-scale AI models in production
- Develop
high-performance inference pipelines
across GPU providers
- Implement infrastructure for
reliable deployment and scaling of AI workloads
- Build systems that
dispatch workloads to GPU clusters and manage capacity
- Optimize performance using
profiling, batching, caching, and scheduling
*MLOps & Reliability*
- Build tooling for
deploying and versioning machine learning models
- Design
CI/CD pipelines for ML systems
- Improve
observability for AI workloads
(metrics, tracing, monitoring)
You will help track and improve:
- Latency
- Reliability
- GPU utilization
- Infrastructure cost
- Model quality signals
*Platform Engineering*
- Build backend services and APIs powering the AI platform
- Collaborate with researchers and engineers to
bring new models into production
- Design systems enabling
rapid iteration with production-grade reliability
- Contribute to architecture decisions around
distributed inference and GPU orchestration
Qualifications
You may have some of the following:
- 8+ years
building production infrastructure, backend systems, or DevOps platforms
or
- 2–3 years
of hands-on
MLOps / AI infrastructure experience
Additional experience:
- Strong
Python backend engineering
experience
- Experience with
model serving or AI infrastructure
- Experience running systems on
AWS or other cloud platforms
- Experience with
distributed systems
- Experience building
high-performance APIs
- Familiarity with
LLMs and AI-assisted development workflows
Nice to have:
- Golang
- GPU infrastructure
- Ray or distributed compute frameworks
- Docker / containerized workloads
- OpenTelemetry or observability platforms
- Autoscaling infrastructure
Why Join Nura Studios
At Nura Studios you will:
- Work on
cutting-edge Generative AI technology for filmmaking
- Build infrastructure for
large-scale AI systems
- Help shape the future of
AI-powered creative tools
- Join a
small, highly experienced engineering team
- Solve challenging problems in
GPU infrastructure, AI deployment, and distributed systems
We offer:
- Flexible vacation
- Remote-first culture
- Compensation package including
salary and equity
- Comprehensive health benefits
- Option to work from our
Old Montreal office
And most importantly — the opportunity to build technology that empowers the
next generation of storytellers.