AI Infrastructure Engineer

1 day, 6 hours ago
Full-time
Senior
DevOps and Infrastructure
Umpisa

Umpisa

Umpisa, Inc. partners with industries to drive pioneering solutions through modern software development, aiming to establish the Philippines as a global tech hub.

Internet Software & Services
11-50
Founded 2019

Description

  • Define the AI infrastructure architecture strategy for the platform.
  • Lead cross-functional collaboration with Data Science and Security teams.
  • Design a multi-region GPU cluster strategy.
  • Evaluate emerging AI infrastructure technologies and establish best practices and governance models.
  • Design and implement inference efficiency initiatives such as prompt and context caching.
  • Build systems that provide fine-grained control over cache prefixes and retrieval strategies.
  • Optimize latency and cost efficiency for large-scale LLM inference workloads.
  • Support Retrieval-Augmented Generation (RAG) architectures.
  • Architect and implement end-to-end encryption for cached AI content.
  • Integrate customer-managed encryption keys (CMEK) within cloud environments.
  • Ensure secure multi-tenant data isolation and compliance standards.
  • Develop enterprise-ready vector similarity search systems and scalable embedding search infrastructure.
  • Optimize ANN algorithms for scale and latency.
  • Build ranking models for personalization, recommendation, and monetization.
  • Design and maintain petabyte-scale distributed storage systems with low-latency queries and high-update throughput.

Requirements

  • 5+ years of experience in Infrastructure/Cloud Engineering and IAM.
  • Extensive experience with large-scale distributed systems.
  • Experience leading technical teams.
  • Strong architectural and documentation skills.
  • Knowledge of AI workload optimization.
  • Experience with hyperscale cloud platforms such as Google Cloud Platform.
  • Familiarity with vector databases and ANN indexing techniques.
  • Exposure to LLM inference optimization techniques.
  • Experience building infrastructure that supports generative AI applications.
  • Background in storage engines similar to Google’s Mesa/Napa architecture.
  • Strong systems design skills.
  • Performance optimization mindset.
  • Security-first engineering approach.
  • Experience building enterprise-ready cloud services.
  • Ability to work in high-scale, production-critical environments.
  • Must align with company values including Excellence, Integrity, Professionalism, People Success, Customer Success, Fun, Innovation, and Diversity.
  • Must be a self-starter who enjoys collaborating with teams and clients.
  • Strong communication and problem-solving skills.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

AI Go-to-Market Engineer (Serbia)

Flosum 51-250 Internet Software & Services

Flosum is hiring its first AI Go-to-Market Engineer to build and optimize AI systems across the revenue engine, with the goal of increasing pipeline, accelerating deals, and reducing churn for its Salesforce-native enterprise platform.

CI/CD CRM JavaScript Python Salesforce SQL
4 hours, 33 minutes ago

AI Automation Engineer

Private In-Home Tutoring & Test-Preparation 51-250 Diversified Consumer Services

Tutor Me Education is hiring its first dedicated automation engineer to build internal AI and workflow automation that streamlines operations across recruiting, onboarding, knowledge access, and document-heavy processes.

Node.js OAuth Python REST API TypeScript
4 hours, 33 minutes ago

Back-End Developer with AI Experience

Wing Assistant 51-250 Professional Services

Wing is hiring a remote Back-End Developer with AI Experience in Manila to build and maintain server-side applications that support AI-driven products and operations automation.

AWS Azure Django Docker GCP Go GraphQL Hugging Face Java Kubeflow Kubernetes Microservices MLflow MongoDB MySQL Node.js PostgreSQL Python PyTorch REST API Spring Boot TensorFlow Vertex AI
4 hours, 33 minutes ago

Compiler Engineer – MLIR / PyTorch Infrastructure

Mythic 51-250 Semiconductors & Semiconductor Equipment

Mythic is seeking a Compiler Engineer to help migrate and extend its compiler stack into MLIR while improving interoperability with PyTorch and other frameworks for its novel AI hardware platform.

C++ Python PyTorch
4 hours, 33 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers