AI Systems & Applications Engineer

Summary
A hands-on engineering role focused on building production-grade AI/ML systems and the automation infrastructure that supports them — driving AI adoption into developer workflows, internal tooling, and domain-specific applications across the organization.

Description
As a member of the AI Infrastructure & Applications team, you will lead the design, development, and production deployment of AI/ML-powered systems alongside the automation infrastructure and developer platforms that support them.

You will architect intelligent, scalable solutions used across the organization — driving AI adoption into developer and automation workflows, internal tooling, and domain-specific applications — while also building and maintaining the automation frameworks and infrastructure those systems depend on.

The systems you build are expected to be production-grade, reliable, observable, and continuously improving.

Responsibilities

• Architect and ship end-to-end AI-powered applications and pipelines, from prototype to production.
• Build agentic systems, RAG pipelines, and tool-use patterns that integrate LLMs into real workflows.
• Define and own AI quality metrics (accuracy, groundedness, hallucination rate, task completion) and integrate them into CI/CD release gates.
• Design evaluation frameworks for non-deterministic systems: offline evals, human-in-the-loop review, and automated regression suites.
• Harness AI/LLMs to extend and enhance existing automation infrastructure, improving system performance and operational efficiency.
• Build scalable automation frameworks, APIs, and tooling used across the organization.
• Collaborate with engineering, CI, and domain teams to address automation needs across hardware, software, and cloud.
• Distill requirements from a large, diverse user base into generic, reusable, maintainable solutions.
• Implement monitoring, drift detection, and structured feedback pipelines for continuous improvement.
• Apply rigorous engineering discipline — test design, release criteria, rollback strategies — to AI-native deployments.
• Partner with product, design, and domain experts to define use cases, acceptance criteria, and rollout plans.
  
  

• BSc in Computer Science, Software Engineering, or related field — or equivalent industry experience.
• Strong programming, system design, and API design skills with a focus on scalability and production-readiness.
• Proficiency in Python for automation, API development and pipeline engineering.
• Experience building automation frameworks, internal developer tools, and shared platforms at scale.
• Solid understanding of prompt engineering, retrieval strategies, context management, and model orchestration.
• Hands-on experience building and deploying LLM-powered systems: agentic pipelines, RAG, tool-use, and function-calling.
• Strong debugging skills across the full AI stack; familiarity with LLM safety and responsible AI practices.
• Experience designing and running AI evaluations — automated and human-in-the-loop — and embedding quality gates into CI/CD release workflows.
  
  

• Experience leading projects end-to-end — from initial scoping and stakeholder alignment through delivery- coordinating across engineering, product, design, and domain teams.
• Practical systems management experience: configuration management, dependency resolution, and deployment tooling across cloud and on-prem environments.
• Ability to design sustainable automation systems serving a large, diverse engineering user base.
• Hands-on experience with orchestration frameworks and managing the full development lifecycle of complex, multi-component systems.
• MA in Computer Science, Software Engineering, or related field.