AI Engineer - AI Foundations and Platform Enablement –
Location: Dallas, TX and Austin, TXHire type: C2H and FTESalary: $60/hr / $120K on FTE
Role Summary
Design and build the foundational platform layers needed to deliver secure, scalable, reusable AI use cases. The role will develop proofs of concept and production-ready patterns across MCP, orchestration, security, caching, and telemetry.
Key Responsibilities- Build POCs for MCP gateways and retail-domain MCP servers that securely expose enterprise tools and data.- Design an orchestration layer for coordinating models, agents, tools, workflows, approvals, retries, and failures.- Establish caching patterns that improve latency and cost while protecting data freshness and privacy.- Implement agentic authentication and authorization, including identity propagation, delegated access, least privilege, and auditability.- Create telemetry for AI workflows, including traces, metrics, logs, token usage, tool calls, latency, errors, and policy decisions.- Deliver reusable APIs, reference implementations, documentation, and standards for application teams.- Partner with architecture, security, product, and engineering teams to move POCs toward production. Must Have
- 5+ years of software engineering experience building distributed services or platforms.- Hands-on experience with LLM applications, AI agents, RAG, or tool-calling workflows.- Strong programming skills in Java, Python, TypeScript, or Go.- Experience with APIs, service integration, asynchronous processing, and distributed systems.- Practical knowledge of authentication, authorization, secrets management, and secure service communication.- Experience with observability, including structured logging, metrics, tracing, and operational dashboards.- Experience with cloud and containerized deployments, such as Kubernetes.- Strong communication and collaboration skills, with the ability to turn ambiguous ideas into working POCs.Nice to Have
- Experience with Model Context Protocol, MCP gateways, MCP servers, or similar agent integration frameworks.- Experience building orchestration or workflow platforms with durable execution, queues, event streams, or human-in-the-loop controls.