AI Platform Engineer

"We are unable to sponsor or take over sponsorship of an employment visa at this time."

AI Platform Engineer

As an AI Platform Engineer, you will design, build, and operate the foundational components of an enterprise AI platform, enabling secure, scalable, and responsible development and deployment of advanced AI and agentic solutions. You will work across the full AI platform stack, from data ingestion and vector databases to retrieval systems, orchestration frameworks, agent platforms, and developer-facing APIs, enabling teams to rapidly deliver innovative AI-powered business capabilities. You will collaborate with security, FinOps, platform engineering, data engineering, and application teams to deliver enterprise-grade AI capabilities that are secure, observable, and cost efficient. Your work will span cloud-native AI services, agentic architectures, orchestration frameworks, and responsible AI guardrails. You will play a critical role in designing and implementing solutions based on Model Context Protocol (MCP), enterprise AI Gateway patterns, and modern agent platforms including Amazon Bedrock and AWS AgentCore. You will help establish the enterprise standards for model access, agent execution, governance, observability, and cost optimization while enabling a multi-model AI ecosystem through AI Gateway technologies such as Kong AI Gateway and similar enterprise platforms.

You can build and maintain AI platform services:

• Design, build, and operate enterprise AI platform capabilities supporting Generative AI, Retrieval-Augmented Generation (RAG), and agentic workloads.

• Develop scalable data ingestion pipelines, knowledge ingestion workflows, and AI data services.

• Integrate vector databases, embeddings, knowledge graphs, and enterprise knowledge repositories with appropriate governance controls.

• Design and implement retrieval frameworks supporting enterprise search, semantic search, and RAG patterns.

• Build and operate AI services using Amazon Bedrock, including foundation model integrations, Bedrock Knowledge Bases, Guardrails, and inference capabilities.

• Design and support agentic architectures utilizing AWS AgentCore and other enterprise agent platforms.

• Implement model serving infrastructure for real-time and batch inference workloads.

• Enable secure agentic workflows through Model Context Protocol (MCP), tool orchestration frameworks, and agent-to-agent communication patterns.

• Design and implement AI Gateway capabilities using technologies such as Kong AI Gateway to provide centralized authentication, routing, governance, observability, rate limiting, and policy enforcement for AI workloads.

• Develop APIs, SDKs, reusable platform services, and self-service capabilities that accelerate AI adoption across engineering teams.

You ensure observability and responsible AI:

• Monitor model performance, application behavior, agent execution, and service reliability.

• Implement logging, tracing, alerting, rollback, and operational recovery mechanisms.

• Monitor AI usage patterns, token consumption, latency, throughput, and AI Gateway telemetry.

• Implement observability solutions that provide visibility into prompts, responses, model behavior, agent interactions, and platform health.

• Apply explainability, fairness, governance, and compliance guardrails consistent with Responsible AI principles.

• Support model evaluation, benchmarking, experimentation, and lifecycle management processes.

You have experience embedding security and compliance:

• Design and implement secure AI platform architectures using cloud-native security controls.

• Integrate encryption, IAM, secrets management, and audit logging capabilities.

• Implement secure access patterns through AI Gateway platforms including authorization, policy enforcement, prompt security controls, and data protection measures.

• Support compliance with regulatory and internal governance frameworks, including privacy, security, and Responsible AI requirements.

• Partner with Information Security, Risk, Compliance, and Data Governance teams to ensure safe and compliant use of enterprise data and AI services.

• Enable governance for models, agents, prompts, tools, and enterprise knowledge sources.

You drive operational excellence:

• Apply Site Reliability Engineering (SRE) practices to ensure reliability, scalability, and operational maturity.

• Apply FinOps principles to optimize AI platform utilization, model consumption, and cloud spending.

• Automate infrastructure provisioning and management using Infrastructure as Code (IaC).

• Establish operational standards, platform runbooks, SLA/SLO metrics, and support procedures.

• Drive continuous improvements in platform security, performance, resiliency, and developer experience.

You collaborate and enable teams:

• Partner with software engineers, platform engineers, architects, and product teams to deliver enterprise AI solutions.

• Consult with application teams on AI platform integration patterns and best practices.

• Create reference architectures, reusable patterns, and implementation guidance.

• Develop documentation, runbooks, architectural diagrams, and operational standards.

• Mentor team members and help promote adoption of enterprise AI platform capabilities.

Required Qualifications

• Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related technical field, or equivalent practical experience.

• 7+ years of experience designing, building, and operating distributed platform technologies or cloud-native systems.

• 3+ years of experience building, operating, or supporting AI/ML platforms and services.

• Hands-on experience with Amazon Bedrock and enterprise foundation model platforms.

• Experience designing and implementing Retrieval-Augmented Generation (RAG) architectures using vector databases, embeddings, and enterprise knowledge sources.

• Experience building or operating agentic AI systems utilizing AWS AgentCore or comparable agent frameworks.

• Experience designing and implementing solutions based on Model Context Protocol (MCP).

• Experience implementing AI Gateway solutions (e.g., Kong AI Gateway or equivalent) for AI governance, traffic management, observability, and security.

• Familiarity with agent orchestration frameworks, agent-to-agent communication patterns, and multi-agent architectures.

• Strong understanding of LLM operations including prompt engineering, model evaluation, guardrails, governance, and token optimization.

• Proficiency in Python and/or other languages commonly used for AI and platform engineering.

• Experience with AWS cloud services, containerization, Kubernetes, and modern CI/CD practices.

• Understanding of observability, monitoring, and operational support for AI and agent-based systems.

• Experience implementing security, privacy, governance, and compliance controls in AI environments.

Preferred Qualifications

• Experience in financial services or other highly regulated industries.

• AWS certifications related to AI, Machine Learning, Cloud Architecture, or Platform Engineering.

• Experience with Amazon Bedrock Knowledge Bases, Bedrock Guardrails, Agents for Bedrock, and AWS AgentCore services.

• Experience with Kong AI Gateway or comparable API and AI Gateway technologies.

• Experience implementing MCP servers, tool catalogs, and secure tool execution frameworks.

• Experience with enterprise multi-model strategies spanning Anthropic Claude, Amazon Nova, OpenAI, Google Gemini, and other foundation models.

• Familiarity with AI-specific observability and monitoring platforms.

• Experience implementing Responsible AI frameworks, guardrails, explainability, and model governance processes.

• Experience with FinOps practices and cost optimization for Generative AI workloads.

• Familiarity with Agile, DevSecOps, and platform engineering practices.

• Experience building enterprise self-service AI platforms and developer enablement capabilities.

Kaleidoscope, an Infosys Company, is an equal opportunity employer, and all qualified applicants will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, spouse of protected veteran, or disability.