GenAI / Agent Platform Engineer

Role: Senior Technology Consultant – GenAI / Agent Platform Engineer

Location: Westlake, Texas and Durham, North Carolina; Hybrid

Job Description:  

Role Summary:

We are seeking an experienced GenAI / Agent Platform Engineer to design, build, and operate enterprise-grade platforms for Generative AI and AI Agent solutions. The ideal candidate should have strong hands-on expertise in agent orchestration, LLM/model integration, tool invocation, prompt engineering and safety, policy controls, and AI observability/telemetry.

The role will collaborate with application engineering, AI/ML, platform, security, and governance teams to build scalable and secure capabilities that enable development teams to create and operate production-grade AI agents and GenAI applications.

Day-to-Day Job Duties:

·         Design and develop enterprise platforms for GenAI applications and AI agents.

·         Build agent orchestration workflows supporting planning, reasoning, tool invocation, and multi-step execution.

·         Integrate enterprise applications with LLMs and foundation models through secure APIs.

·         Develop reusable agent capabilities, tools, APIs, connectors, and platform services.

·         Implement tool/function calling to enable agents to securely interact with enterprise systems and data sources.

·         Build and manage integrations using Model Context Protocol (MCP) where applicable.

·         Implement prompt management, versioning, templates, and reusable prompt libraries.

·         Develop prompt safety and security controls, including input/output filtering and prompt-injection defenses.

·         Implement policy controls governing model access, tool permissions, data access, and agent behavior.

·         Develop guardrails to support responsible and secure use of Generative AI.

·         Implement telemetry, tracing, logging, metrics, and observability across agent and LLM workflows.

·         Monitor model/agent performance, latency, token consumption, failures, and operational health.

·         Build automated evaluation and testing capabilities for prompts, models, tools, and agent workflows.

·         Collaborate with security and governance teams to implement auditability and appropriate AI controls.

·         Troubleshoot production AI/agent issues and continuously improve platform reliability and performance.

Basic Qualifications:

·         7+ years of experience in Software Engineering, Platform Engineering, AI/ML Engineering, or cloud-native application development.

·         3+ years of hands-on experience developing Generative AI, LLM-integrated applications, or AI Agent solutions.

·         2+ years of experience with agent orchestration, model integration, tool/function calling, and production LLM APIs.

·         2+ years of experience implementing AI observability, security/guardrails, policy controls, or production AI platform capabilities.

Technical Skills:

·         Agentic AI: Agent Orchestration, Tool Calling, Multi-Agent Workflows, Agent Lifecycle

·         Agent Frameworks: LangGraph, LangChain, CrewAI, AutoGen, Strands or similar

·         Model Integration: AWS Bedrock, Azure OpenAI/AI Foundry, OpenAI APIs, Anthropic APIs

·         Agent Integration: Model Context Protocol (MCP), APIs, Enterprise Connectors

·         GenAI: Prompt Engineering, RAG, Embedding’s, Vector Search

·         AI Safety: Guardrails, Prompt-Injection Defense, Content Filtering, Policy Enforcement

·         Observability: Agent/LLM Tracing, Logging, Metrics, Evaluation, Token & Latency Monitoring

·         Engineering: Python, Java, TypeScript, or similar programming languages

·         Platform: REST APIs, Microservices, Docker, Kubernetes

·         Cloud: AWS and/or Microsoft Azure

·         DevOps: GitHub, CI/CD, Automated Testing

Nice to Have:

·         Experience developing MCP servers or MCP-enabled integrations.

·         Experience building production solutions with LangGraph, Strands, LangChain, AutoGen, CrewAI, or Bedrock Agents.

·         Experience with AWS Bedrock, Azure AI Foundry, OpenAI, or Anthropic in production environments.

·         Experience building enterprise RAG platforms, vector stores, and knowledge retrieval services.

·         Knowledge of agent memory, context management, and conversation state management.

·         Experience with LLM evaluation and observability platforms such as Langfuse, LangSmith, Braintrust, or Weights & Biases.

·         Experience implementing human-in-the-loop approval and escalation workflows.

·         Knowledge of Responsible AI, model governance, data privacy, and audit requirements.

·         Experience implementing role-based access controls and fine-grained permissions for agents and tools.

·         Experience with Kubernetes and cloud-native AI platforms.

·         Strong understanding of API security, OAuth/OIDC, IAM, secrets management, and secure engineering.

·         Experience building reusable enterprise AI platforms or internal developer platforms.

·         Strong software engineering, architecture, troubleshooting, communication, and problem-solving skills