- Company Name
- S.i. Systems
- Job Title
- Senior AI Platform Engineer
- Job Description
-
Job Title: Senior AI Platform Engineer
Role Summary
Design, build, and maintain a scalable, secure, and reusable Agentic AI platform that serves diverse enterprise AI use cases. Deliver core platform services, orchestrate multi‑agent workflows, and enable data scientists and developers through APIs, SDKs, and developer tooling while upholding safety, governance, and observability standards.
Expectations
- Lead the creation of foundational AI and multi‑agent services with a focus on automation‑first delivery.
- Ensure platform reliability, security, compliance, and performance across cloud, distributed, and AI‑specific workloads.
- Collaborate with AI, security, and regional teams to localize the platform for global deployment and regulatory requirements.
- Mentor engineering and data‑science teams on agentic design patterns.
Key Responsibilities
- Develop and operate AI platform services and abstractions supporting diverse AI use cases.
- Build reusable reference components, inner‑source patterns, and shared runtimes for agent coordination, state, memory, and messaging.
- Design interoperable APIs/SDKs for data scientists and developers.
- Maintain and enhance CI/CD pipelines, developer toolchains, and observability for AI services.
- Prototype and evaluate emerging AI/ML infrastructure tools to boost productivity and reliability.
- Construct scalable backend services for high‑traffic agent interactions, real‑time execution, and retrieval operations.
- Optimize CPU/GPU/accelerator workloads and cloud‑native runtimes (containers, orchestration, IaC).
- Implement standardized retrieval frameworks, embeddings, and knowledge connectors.
- Build and maintain short‑term and long‑term memory abstractions for agent workflows.
- Create tool interfaces for enterprise systems, APIs, databases, and automations with safe execution and auditability.
- Develop AI governance, safety, and observability frameworks (traces, logs, metrics, feedback loops).
- Provide templates, scaffolding, and CLI tools to accelerate agent‑powered application development.
Required Skills
- 5+ years of backend/platform/cloud systems engineering experience (e.g., Jenkins, GitHub, Terraform).
- Proficient in Python; strong knowledge of Java, Scala, or TypeScript for backend services.
- Experience with Azure Kubernetes Services (AKS), containers, CI/CD, and IaC.
- Deep understanding of LLM systems, retrieval architectures, embeddings, vector stores, and prompt/tool orchestration.
- Ability to design secure, scalable, and API‑centric services.
- Strong grasp of observability, monitoring, logging, and performance tuning.
- Experience with governance, safety, and compliance frameworks for AI systems.
Required Education & Certifications
- Bachelor’s degree in Computer Science, Software Engineering, or related field.
- Certifications in cloud platforms (Azure, AWS, GCP) and CI/CD tools are a plus.