Software Engineer (ML Infrastructure), London
Isomorphic Labs
Overview
In this role you will help build and operate our inference platform, delivering ML model fleets to scientific applications. You will combine distributed systems expertise with Kubernetes operation to ensure scalable, reliable production services. You will support users, improve CI/CD, and build observability and docs. You will work in a fast-paced, ambiguous environment with strong ownership and user focus. You will contribute to IsoLabs' mission to advance drug discovery with AI.
Responsibilities- Contribute to development and operation of the inference platform for ML model fleets
- Deliver high-quality, well-tested user-focused features
- Provide support to platform users
- Maintain and drive internal tech investments for stability, reliability, and scalability
- Build observability and alerting mechanisms for the platform
- Improve CI/CD setup for the platform
- Operate effectively in a fast-paced, ambiguous environment with autonomous delivery
- Provide documentation and guidance for contributors and users
- Experience writing and maintaining production Python code with concurrency (async, threads, processes, GIL)
- Experience building, maintaining, and operating Kubernetes services
- Experience working with distributed systems
- Experience maintaining APIs serving a moderate internal user base
- Experience with ML models and understanding ML lifecycle in serving/operating workloads
- Independence
- Strong ownership
- User focus
- Python production code
- Kubernetes
- Distributed systems
Reference: WJ-747_30493350