Project Role : AI Infrastructure Architect
Project Role Description : Architect and build custom Artificial Intelligence (AI) infrastructure/hardware solutions. Optimize AI infrastructure/hardware performance, power consumption, cost and scalability of computational stack. Advise on AI infrastructure technology and vendor evaluation, selection and full stack integration.
Must have skills : Agent Development
Good to have skills : NA
Minimum 7.5 year(s) of experience is required
Educational Qualification : 15 years full time education
Level Senior Level
Experience 5 to 8 Years
Work Mode Remote or Hybrid
Employment Full Time
Key Responsibilities
Build multi agent orchestration systems using
Vertex AI
Agent Builder
LangGraph
AutoGen
Design scalable and resilient pipelines integrating
LLM reasoning
Tool calling
Memory management
Human in the loop flows
Lead the design and implementation of RAG systems using
Vertex AI Search
Matching Engine
Enterprise vector stores
Define and enforce GCP infrastructure standards using a security first approach across
GKE
Cloud Run
Eventarc
Apigee
Drive MLOps practices including
Model evaluation
Agent observability
Tracing
Logging
Continuous improvement loops
Partner with product, data science, and platform teams to translate business requirements into agentic solutions
Conduct in depth code reviews
Conduct architecture reviews
Mentor developers with 3 to 5 years of experience
Contribute to
Internal developer platforms
SDKs
Reusable agent components
Required Skills and Qualifications
5 to 8 years of software or platform engineering experience
2 or more years focused on AI ML or agentic systems
Deep expertise in GCP services including
Vertex AI
Gemini
Vertex AI Pipelines
Feature Store
GKE
Pub Sub
Proven experience building production grade LLM powered applications with
Tool use
Multi turn reasoning
Agent memory
Proficiency in Python
Strong understanding of
Async patterns
Concurrency
Distributed systems
Hands on experience with agentic frameworks such as
ADK
LangChain
LangGraph
CrewAI
Experience with
Vector databases
Embedding pipelines
Hybrid search architectures
Strong command of GCP security including
IAM
Workload Identity
VPC Service Controls
Secret Manager
Track record of delivering
High availability services
Low latency services
SLO SLA ownership
15 years full time education
