AI Engineer

Sr. AI Engineer

We’re looking for a hands-on GenAI Engineer to help design and build an enterprise-grade agentic AI platform, enabling AI-driven solutions that can plan, orchestrate tools, and execute multi-step workflows safely and reliably. This is a highly technical, build-focused role for someone who enjoys turning GenAI concepts into production systems.

Location: Phoenix, AZ (Hybrid)

What you’ll do

• Architect, design, and deliver production-grade GenAI/agentic AI systems for enterprise use cases.
• Build AI agents that use LLMs, tool/function calling, workflow orchestration, memory patterns, and enterprise integrations.

Design and optimize core GenAI capabilities such as:

• Prompt & context engineering
• Retrieval-Augmented Generation (RAG) / knowledge retrieval
• Model selection, evaluation, and guardrails
• Build and maintain cloud-native services (Azure/AWS/GCP) with strong engineering practices (CI/CD, testing, observability).
• Integrate agents securely with enterprise apps/APIs/data sources using modern integration patterns (REST, webhooks, event-driven messaging).
• Establish best practices around AI governance, security, monitoring, reliability, and responsible AI.
• Support production deployments (performance tuning, troubleshooting, continuous improvement).
• Provide technical leadership through design reviews, code reviews, and mentorship (non-manager track).

What we’re looking for

• 7+ years of software engineering experience, including 2–3+ years delivering Generative AI, LLM, or conversational/agentic solutions.
• Strong experience building with LLMs (e.g., OpenAI/Azure OpenAI, Anthropic, Gemini, or similar) in real applications.
• Experience with modern GenAI frameworks (e.g., LangChain/LangGraph, Semantic Kernel, or similar).
• Solid cloud engineering background (Azure preferred), including Docker/Kubernetes, serverless, and Infrastructure-as-Code concepts.
• Strong integration skills and familiarity with enterprise auth patterns (OAuth/OIDC/SAML).
• Practical experience with:
• Vector search / hybrid retrieval
• Embeddings, reranking, evaluation strategies
• Observability for GenAI pipelines (tracing, token/cost monitoring, grounding quality)

Nice to have

• Multi-agent orchestration patterns (planner/executor, ReAct-style approaches)
• LLMOps / eval-driven development (regression suites, golden datasets, prompt/agent versioning)
• Knowledge graphs / GraphRAG experience