About The Position

Apple is seeking a senior engineer to own the correctness, consistency, and stability of LLM inference in production. The role designs and builds automation frameworks, evaluation methodologies, and qualification strategies for model, prompt, serving-stack, and infrastructure changes before deployment. The engineer leads qualification of LLM inference and output-correctness automation for large-scale AI data center deployment and platform validation. They architect systems for generative AI, including agentic workflows and tool-using models, and validate output correctness, consistency, and stability as models, weights, prompts, runtimes, quantization schemes, and accelerator hardware change. This hands-on AI systems engineering role spans machine learning, distributed systems, and quality engineering. It involves production-quality software development, statistical and ML-evaluation methods, and AI-assisted QA tooling. The engineer partners with ML, inference/performance, distributed systems, and platform teams, and defines what correctness and stability mean for probabilistic LLM inference at scale. The role requires operating in ambiguity and delivering rigorous results on tight schedules.

Requirements

  • At least 5 years of experience with hardware and/or software development lifecycle processes.
  • At least 5 years of experience in one or more compiled languages, such as C, C++, Objective-C, or Swift.
  • Proficiency in one or more scripting languages, such as Python, Go, or JavaScript.
  • Experience using AI/LLMs to improve testing, such as test-case generation, defect detection, or reducing manual QA effort.
  • Familiarity with LLM serving and inference optimization, including batching, KV-cache, quantization, speculative decoding, distributed/multi-accelerator serving, and GPU-accelerated software.
  • Experience with CI/CD, Kubernetes, containers, cloud-native systems, and integrating automated evaluations into release pipelines.
  • Experience with machine learning and LLMs, their practical applications, and commonly used frameworks such as PyTorch, Hugging Face Transformers, or comparable inference/serving stacks.
  • Experience with observability and distributed tracing for ML systems and monitoring for model drift.
  • B.S., M.S., Ph.D. in Computer Engineering, Electrical Engineering, or Computer Science, or equivalent experience.

Nice To Haves

  • At least 5 years using one or more scripting languages: Python, Go, or JavaScript.
  • At least 5 years of experience working with and building operating systems.
  • At least 2 years of experience in LLM testing/development.

Responsibilities

  • Lead qualification of LLM inference and output-correctness automation for large-scale AI data center deployment and platform validation.
  • Architect qualification systems for generative AI, including agentic workflows and tool-using models.
  • Validate that outputs remain correct, consistent, and stable as models, weights, prompts, serving runtimes, quantization schemes, and accelerator hardware change.
  • Write production-quality software in Python, C++, and/or Swift.
  • Apply statistical and machine-learning evaluation methods to validate data and model behavior.
  • Build AI-assisted QA tooling to make testing smarter and faster.
  • Partner with ML engineers, inference/performance engineers, distributed systems engineers, and platform teams.
  • Define quality standards for correct and stable LLM inference at scale, including probabilistic and non-deterministic output.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service