Overview
As part of the AI Platform team, you will play a key role in building the foundational infrastructure, frameworks, and tooling that enable AI-powered products and capabilities across the organization. This role requires a high degree of autonomy and ownership, as you will be responsible for designing scalable solutions that empower multiple engineering teams while ensuring reliability, observability, and cost efficiency.
Key Responsibilities
- Design, build, and maintain a robust, scalable, and cost-effective AI Platform that supports AI initiatives across the organization.
- Develop and maintain internal frameworks, libraries, and services used by multiple product squads.
- Establish and promote best practices around prompt engineering, AI guardrails, and AI evaluation methodologies.
- Build platform capabilities that enable teams to safely deploy, monitor, and iterate on AI-powered applications.
- Configure and maintain tracing, monitoring, observability, and incident management solutions to ensure platform reliability.
- Partner closely with product and engineering teams to understand their needs and provide scalable platform solutions.
- Continuously improve developer experience and platform adoption across the organization.
Technical Stack
- Python FastAPI, Agent Development Kit (ADK)
- Datastores: PostgreSQL, BigQuery, Firestore
- Infrastructure: Google Cloud Platform (GCP)
- Messaging: RabbitMQ
- Infrastructure as Code: Terraform
- Monitoring & Observability: Grafana, Prometheus, Langfuse, incident.io, Sentry
Qualifications
- 5+ years of experience in Software Engineering, Backend Engineering, or Platform Engineering.
- Strong experience building and maintaining backend systems and distributed services in production environments.
- Experience designing developer platforms, internal tooling, shared services, or infrastructure that supports multiple engineering teams.
- Hands‑on experience building AI-powered applications and services using modern LLM frameworks and agentic architectures.
- Good understanding of modern AI concepts and practices, including Large Language Models (LLMs), Retrieval‑Augmented Generation (RAG), Prompt Engineering, AI Guardrails, AI Evaluation Frameworks.
- Experience with AI frameworks such as Agent Development Kit (ADK), LangChain, LangGraph, CrewAI, or similar.
- Experience working with cloud platforms such as Google Cloud Platform (preferred), AWS, or Azure.
- Strong understanding of system reliability, observability, monitoring, and incident management.
- Experience with Infrastructure as Code and cloud‑native architectures.
- Previous experience working within a Platform Engineering team is a strong plus.
Plum is an Equal Opportunity Employer. Plum does not discriminate on the basis of age, race, religion, sex, gender identity, sexual orientation, non‑disqualifying physical or mental disability, national origin or any other basis covered by appropriate law. All employment is decided on the basis of qualifications, merit and business need.
#J-18808-Ljbffr…