Sr. AI Engineer (Applied AI & ML Systems)

What You’ll Do (Essential Responsibilities):

• Design, build, and deploy AI solutions powered by ML, LLMs, and agentic AI systems that solve real business problems.
• Define evaluation strategies upfront for each use case, including task success metrics, offline and online evaluation plans, error analysis, and production monitoring requirements.
• Build and improve LLM-based systems using prompt engineering, retrieval-augmented generation (RAG), context engineering, and multi-step agentic workflows.
• Partner closely with product, engineering, data, and business stakeholders to prioritize AI use cases and align on success metrics, operational requirements, and delivery timelines.
• Apply strong production practices across AI systems, including experimentation, versioning, observability, alerting and continuous improvement in production.
• Monitor, troubleshoot, and improve production AI systems by balancing quality, latency, cost, reliability, and maintainability.

Who You Are (Soft Skills & Attributes):

• You bring an evaluation-first mindset and believe AI systems should not be designed or implemented without a clear plan to measure quality, risk, and business impact.
• You are thoughtful, practical, and systems-oriented, with sound judgment about when to experiment, when to simplify, when to stop, and when to productionize.
• You take ownership of outcomes, learn from mistakes, and use feedback and new evidence to continuously improve your thinking, your systems, and your results.
• You are comfortable working in ambiguity, asking questions, challenging assumptions, and collaborating across technical and non-technical teams to solve complex problems.

What You’ll Need (Required Knowledge, Skills & Abilities):

• Bachelor's degree in Computer Science or a related field, and knowledge, skills, and abilities typically associated with 6+ years of relevant experience, including:
  • 4+ years of experience in one or more of the following areas:
    • Machine Learning or Applied Modeling
    • Data Engineering
    • Software Engineering for Data-Intensive Systems.
• 2+ years of experience building LLM-based applications, including at least 1 year building agentic AI systems as part of that experience.
• Experience building and operating production data pipelines, data platforms, or large-scale data-intensive systems.
• Hands-on experience building LLM-powered applications, including context engineering, retrieval-augmented generation (RAG), evaluation frameworks, prompt engineering and optimization. Experience with model fine-tuning is preferred but not required.
• Experience designing and implementing agentic AI systems, including multi-step workflows that incorporate planning, memory, handoffs, tool orchestration, and human-in-the-loop review.
• Strong track record of defining evaluation strategies upfront and operating AI systems in production, including deployment, monitoring, observability, versioning, experimentation, and continuous improvement.
• Advanced Python skills and experience taking AI solutions from prototype to production while balancing quality, latency, cost, reliability, and maintainability.

What Would be Nice (Preferred Skills & Experience):

• Experience with vector databases, graph databases, retrieval quality tuning, and domain-specific optimization for LLM-based systems.
• Experience designing reusable AI platforms, shared services, internal tooling, or infrastructure that improves AI development speed, consistency, and reuse.
• Experience with cloud-native AI deployment, distributed systems, and scalable serving infrastructure for ML, LLM, and agentic AI applications.

Why This Role Matters:

This role matters because we need more than someone who can build AI features. We need someone who can build AI systems in a thoughtful and reliable way. That means starting with a clear plan for how quality, risk, and business impact will be measured, and carrying that through design, launch, monitoring, and ongoing improvement.