AI Platform/ DevOps Engineer
The Portfolio Group
- London, England, United Kingdom
- London, England, United Kingdom
Über
The role
This is a platform and infrastructure engineering role - not a data science or ML engineering position. You'll own the runtime, infrastructure, and operational layers that RAG pipelines, LLM orchestration, vector search, and evaluation workflows run on, across AWS and Databricks. The focus is on building scalable, observable, secure, and cost-efficient platform infrastructure that enables AI engineering teams to ship and operate AI products reliably in production.
What you'll do
Design, build, and operate cloud-native AI platform infrastructure across AWS (Lambda, API Gateway, DynamoDB, S3, CloudWatch) and Databricks
Deploy and operate containerised services on Kubernetes using Terraform for infrastructure-as-code
Own and scale vector search infrastructure (OpenSearch, Algolia, AWS Bedrock Knowledge Bases) and embedding pipelines
Build and maintain CI/CD pipelines for inference services, retrievers, ingestion workflows, and RAG components
Implement observability across AI workloads using CloudWatch, MLflow, and OpenTelemetry - covering latency, throughput, cost, and system health
Apply secure-by-design principles including IAM, encryption, network controls, and audit logging
Work closely with AI engineers to translate prototypes and proof-of-concepts into production-ready, well-architected platform components
What we're looking for
Proven experience in platform, infrastructure, or software engineering roles delivering production-grade systems on AWS
Strong hands-on Kubernetes experience, specifically with EKS (Elastic Kubernetes Service) and ECS (Elastic Container Service) in production environments
Strong Terraform experience for infrastructure-as-code, provisioning and managing cloud infrastructure at scale
Experience operating containerised services, managing CI/CD pipelines, and owning observability and reliability
Familiarity with vector databases or search infrastructure (OpenSearch, Algolia) is a strong advantage
Python proficiency for scripting, automation, and deploying production services
Solid grasp of distributed systems, cloud-native architecture, microservices, and API design
Ownership mindset - comfortable operating autonomously across reliability, performance, cost, and security
Why join? You'll own the foundational platform infrastructure behind a growing suite of generative AI products, working directly with senior AI and engineering leaders. This is a deep technical ownership role with long-term architectural impact, within an organisation investing heavily in AI at scale.
INDAM
The Portfolio Group are acting on behalf of our client in recruiting for this position.
Sprachkenntnisse
- English
Hinweis für Nutzer
Dieses Stellenangebot stammt von einer Partnerplattform von TieTalent. Klick auf „Jetzt Bewerben”, um deine Bewerbung direkt auf deren Website einzureichen.