Related skills
data pipelines observability cost optimization model serving llm inference📋 Description
- Design and operate scalable AI infra for LLM inference, prompts, and evaluation pipelines.
- Build self-service tools, SDKs, and APIs to speed prod adoption by ~30%.
- Instrument prod AI/ML workloads with logging, tracing, and metrics for full observability.
- Implement routing, caching, and provider optimization via LLM gateway to cut costs.
- Drive adoption of shared platform services to increase AI feature adoption.
- Champion developer experience with documentation and responsive support.
🎯 Requirements
- Built and deployed production AI infra with enterprise reliability and observability.
- Delivered self-service tools/APIs enabling teams to accelerate AI/ML work.
- Implemented evaluation frameworks, A/B testing, or monitoring for performance, latency, and cost.
- Led cost-reduction efforts via routing or caching optimisations.
- Migrated teams to shared platform services, driving adoption.
- Improved developer experience via better docs, support, and workflows.
🎁 Benefits
- £5,000 training and conference budget
- 33 days total holiday (25 days + 8 bank holidays)
- Company pension via Penfold
- Mental health support via Spectrum.life
- Private healthcare via AXA
- Cycle to Work Scheme
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!