Senior AI Engineer – Agentic AI Platform | Hybrid (Dallas, TX or Chicago, IL)
Pay range: $70–$85/HR (DOE and C2C vs W2)
About the Opportunity
Join a large, data-driven enterprise organization building a next-generation agentic AI platform from the ground up. This isn't a single-agent project — it's a foundational platform effort that will let business and engineering teams across the company build, deploy, and operate AI agents on a shared, secure, and observable enterprise backbone. If you want to shape how an entire organization does agentic AI — not just ship one agent — this is that role.
Hybrid onsite Tuesday–Thursday, based in either Dallas, TX or Chicago, IL.
What You'll Do
- Architect and build reusable platform services that support multiple agent frameworks, models, and business domains — not one-off agent solutions.
- Establish standard patterns for how agents register, discover each other, execute tasks, manage memory/state, and interoperate across systems.
- Design multi-agent orchestration using event-driven and workflow-based approaches, including routing, task delegation, retries, and failure handling.
- Build a centralized gateway for AI model calls, agent tools, and external service integrations, with consistent auth, throttling, and policy enforcement baked in.
- Stand up full observability for agentic systems: distributed tracing, metrics, dashboards, and visibility into agent decisions, tool calls, latency, and failures.
- Build automated evaluation pipelines — benchmarks, regression tests, guardrails — that keep agent quality and safety in check as the platform scales.
- Partner closely with architecture, security, and governance teams to bake in responsible‑AI and secure‑by‑design practices from day one.
What You Bring
- 5+ years of software engineering experience, with meaningful hands‑on time building AI/ML or agentic applications that made it to production (not just prototypes).
- Strong Python skills and real experience designing APIs, microservices, or event-driven/distributed systems.
- Practical experience with LLM‑based systems: agent design patterns, prompt engineering, retrieval‑augmented generation, and tool/model integration.
- Hands‑on experience with at least one agent or orchestration framework (LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or similar) — we care more about depth of use than which one.
- Solid grounding in cloud platforms, containers, CI/CD, and production support practices.
- Observability chops: structured logging, metrics, tracing, alerting.
- A self‑directed, curious engineer who can ramp on new tools and problem domains without needing a formal onboarding path.
- Bachelor's degree in a technical field or equivalent practical experience.
Nice to have: OpenTelemetry or similar distributed‑tracing implementation experience, prior work building model/tool gateways or shared platform services, exposure to LLM/agent evaluation and red‑teaming practices, and background in regulated or data‑intensive enterprise environments.
Logistics
- Contract type: W2 or CSC - Contract-to-Hire or Contract
- Location: Dallas, TX or Chicago, IL metro
- Interview process: Technical video screening required for all candidates (camera on, no headphones during screening)