Sr Applied AI Engineer

Key Responsibilities:

• Drive AI innovation and rapid experimentation to advance capabilities (agentic workflows, reasoning approaches, evaluation methods, and emerging techniques).
• Design and execute timeboxed pilots with clear hypotheses, success metrics, and kill/scale decision points.
• Enhance and evolve existing enterprise AI patterns and standards (e.g., retrieval-augmented generation, text-to-SQL, evaluation/observability, guardrails) using new approaches and measured outcomes.
• Build reference implementations and handoff documents so successful experiments transition into scalable architectures in partnership with the Central AI team.
• Develop within the AWS ecosystem using secure, observable, cost-aware architectures and strong software engineering practices.
• Communicate results through demos and concise readouts that connect technical outcomes to business value, tradeoffs, and recommended next steps.
• Support priority project work as cycles allow, focused on de-risking and acceleration with clear entry/exit criteria.
• Continuously evaluate emerging AI tools, frameworks, and vendor offerings; synthesize external research, OSS trends, and vendor capabilities into actionable recommendations.

Requirements

Required Qualifications:

• 5+ years of software engineering experience (or equivalent), delivering production-quality systems.
• Expert Python skills (clean architecture, testing, packaging, performance and reliability).
• Strong AWS architecture and development experience (security/IAM, networking, serverless and/or containers, monitoring/logging, cost controls).
• Strong data foundations: SQL, data modeling, APIs/integration patterns; comfortable incorporating RAG and text-to-SQL patterns into real solutions.
• Demonstrated rigor in experimentation: hypothesis-driven approach, evaluation plans, metrics, timeboxing, and pragmatic decision-making.
• Ability to communicate clearly to both technical and business stakeholders; proven storytelling and influence through results.
• Bachelor s degree in Computer Science/Engineering (or equivalent practical experience).
• Hands-on experience designing and interpreting LLM evaluations (task success, faithfulness, hallucination analysis, cost/latency tradeoffs).
• Familiarity with modern LLM application stacks across vendors, with an ability to reason about abstraction tradeoffs, portability, and long-term maintainability.
• Hands-on experience with agentic systems (tool use, memory strategies, multi-agent orchestration) and reliability/evaluation techniques.

Preferred Qualifications:

• Experience with Dataiku (DSS), including building and operationalizing analytics/AI workflows; LLMOps experience is a plus.
• Experience building evaluation harnesses (golden sets, regression testing, error analysis) and partnering on risk/safety reviews.
• Exposure to OpenAI AgentKit/ChatKit and Apps SDK/MCP is a plus.
• Experience transitioning prototypes into enterprise-ready patterns in partnership with platform and delivery teams.