Senior AI Platform Engineer

Scrums.com is looking for a Senior Python / AI Platform Engineer to help shape their client's next-generation AI infrastructure platform, bringing open-weight LLMs into secure, customer-controlled production environments.This is a hands-on engineering role at the intersection of backend platform work and applied AI infrastructure, not a research or data-science position. Model strategy sits with the client's ML lead, so your focus stays on building the systems that make AI models run reliably, securely, and at scale.You'll own the design and delivery of production Python services, model-serving APIs, and event-driven architecture, with real technical autonomy and end-to-end ownership of the infrastructure you build.A strong fit for a senior engineer who wants to work close to the AI stack (model serving, inference, GPU/CPU environments) while staying grounded in solid software engineering fundamentals: APIs, microservices, observability, and cloud-native deployment.

Responsibilities

• Design, build and maintain production Python APIs and services using FastAPI or comparable frameworks
• Develop microservices and event-driven systems using Kafka and MongoDB
• Deploy and manage workloads on Microsoft Azure using containers
• Implement and operate open-weight/local LLM deployments (e.g. Gemma or comparable models)
• Build and maintain model-serving and inference APIs with structured model outputs
• Manage model versioning, LLM evaluation/testing, and GPU/CPU inference environments
• Drive observability, performance monitoring, and resource optimization across AI infrastructure
• Support private, customer-controlled AI deployments in line with client security and compliance requirements

Experience and education

• Minimum 7+ years of professional software engineering experience with strong production Python experience
• Proven experience building production APIs/services with FastAPI or a comparable framework
• Hands-on experience with Kafka, event-driven architecture and MongoDB
• Experience with Microsoft Azure and containerization
• Experience deploying open-weight/local LLMs such as Gemma or comparable models
• Experience with model-serving/inference APIs and structured model outputs
• Familiarity with model versioning, LLM evaluation/testing, and GPU/CPU inference environments
• Strong grounding in observability, performance tuning and resource optimization