Principal AI Engineer

Job Description

Key Responsibilities

Architecture Strategy & Design

• Design and deploy scalable, secure, and resilient cloud-native AI infrastructure utilizing AWS (e.g., Bedrock, SageMaker, AgentCore), Azure (e.g., Azure OpenAI, Azure Machine Learning, Microsoft Foundry), or GCP (e.g., Vertex AI, Agent Builder, Agentspace, Gemini Enterprise).
• Define blueprint patterns for advanced AI workloads, including Retrieval-Augmented Generation (RAG), semantic search optimization, and multi-agent orchestration and fine-tuning frameworks.

Agentic AI Systems

• Architect autonomous and multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, or cloud-native equivalents (Bedrock Agents, Azure AI Agent Service, Vertex AI Agent Builder).
• Design agent orchestration patterns — planning, tool-calling, memory, and inter-agent communication — using protocols such as Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication standards.
• Establish guardrails, human-in-the-loop checkpoints, and evaluation frameworks specific to agentic workflows to manage autonomy risk, hallucination propagation, and cascading tool-call failures.
• Define reusable agent design patterns (single-agent vs. multi-agent, hierarchical vs. peer-to-peer orchestration) applicable across business domains.

LLMOps & Production Engineering

• Architect robust LLMOps/MLOps pipelines to automate data ingestion, evaluation, versioning, and deployment.
• Design systems for real-time observability — establishing metrics, dashboards, and alerting frameworks for token consumption, drift, latency, throughput, agent-loop failures, and automated rollback strategies.
• Implement cost-management strategies (e.g., model caching, compute rightsizing, reserved cloud instances, agent-call budget controls) to optimize infrastructure spend.

Governance, Security & Responsible AI

• Collaborate with security and compliance teams to enforce defense-in-depth principles (RBAC, private network segmentation, VPCs, and IAM encryption) for secure AI environments.
• Extend governance frameworks to agentic systems — action-level permission, tool-access scoping, and audit trails for autonomous decision-making.

Technical Leadership & Collaboration

• Serve as a trusted advisor to senior executives and cross-functional business heads, translating complex technical AI capabilities into clear business value.
• Mentor data scientists, MLOps engineers, and software developer teams, contributing reusable code, reference architectures, and Infrastructure-as-Code (IaC) templates.

Required Qualifications

• Deep, demonstrable expertise in at least one hyperscaler (AWS, Azure, or GCP); cloud AI/ML certifications (e.g., AWS Solutions Architect, AWS AI Practitioner, GCP Professional Cloud Architect, Azure AI Engineer) strongly preferred.
• Proven experience architecting and shipping Generative AI / LLM solutions at enterprise scale — RAG pipelines, semantic search, fine-tuning, and prompt/context engineering.
• Hands-on experience building or architecting multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, Bedrock Agents, Azure AI Agent Service, or Vertex AI Agent Builder.
• Working knowledge of agent interoperability protocols such as Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication.
• Strong background in MLOps/LLMOps tooling — CI/CD for ML, model versioning, evaluation frameworks, and observability platforms (e.g., Arize, LangSmith, Datadog, or cloud-native equivalents).
• Solid grounding in AI governance, security, and responsible AI practices - IAM, VPC/network segmentation, data classification, RBAC, and audit/traceability for autonomous systems.
• Track record of translating business problems into scalable, production-ready AI architecture — including cost optimization (FinOps for AI) and infrastructure rightsizing.
• Bachelor's/Master’s/Phd. in Computer Science, Engineering, or related field;

Required Skills

• AI Architecture - Agentic & Integration
• AI Architecture - Data & Model
• AI Architecture - Platform & Operations
• Solution Architecture
• Technical Architecture
• English