Software Engineering Manager, AIML - LLM Inference Quality

Apple Inc.
Seattle, WA, United States
1 day ago
Apply on www.jobmonkeyjobs.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Experienced
Experience required
3 years minimum
Compensation
$195,700
Working hours
Regular working hours

Tech stack

C (Programming Language) Artificial Intelligence C++ (Programming Language) Cloud Computing Computer Engineering Continuous Integration Data Centers Information Leak Prevention Distributed Systems Python (Programming Language) Machine Learning Inference Optimization
+21 more
Prometheus Software Engineering Data Logging Scripting Pytorch Delivery Pipeline Large Language Models Grafana Agentic-AI Discretization LangSmith Kubernetes Information Technology HuggingFace Machine Learning Operations Drift Detection Objective C++ Model Inference Splunk Artificial Intelligence Markup Language (AIML) Dynatrace

Job description

Apple is building the next generation of AI data center infrastructure to power large language model (LLM) services at scale. We are looking for a hands-on engineering manager to lead the team that owns the Quality, correctness, consistency, and stability of LLM inference in production.

Your team builds the automation frameworks, evaluation methodology, and qualification strategy that give Apple confidence in every model, prompt, serving stack, and infrastructure change before it reaches users. This is the safety net that lets Apple ship frontier AI quickly - without sacrificing quality, safety, or trust. We are seeking a deeply experienced manager who stays close to the technology to drive both the technical roadmap and the delivery of a high-performing team., As a technical manager, you will lead a team of engineers spanning quality engineering, distributed systems, and applied ML evaluation. Your team qualifies LLM inference and output-correctness automation frameworks for large-scale AI data center deployment and platform validation - validating that outputs remain correct, consistent, and stable as models, weights, prompts, serving runtimes, quantization schemes, and accelerator hardware change underneath them., Build, mentor, and manage an inclusive team of high-performing engineers; drive hiring and onboarding, manage performance, and prioritize team health and growth paths.

Define the strategic vision and technical roadmap for LLM inference qualification - output-correctness automation, regression and CI gating, agentic-behavior validation, and infrastructure-level inference validation.

Drive execution of complex, multi-quarter projects end-to-end, balancing rapid iteration against long-term architectural stability and a high quality bar.

Champion engineering excellence in evaluation methodology: test-and-qualification strategy across unit, integration, regression, and end-to-end layers for distributed ML serving systems.

Partner cross-functionally with ML, performance, distributed systems, security, privacy, and platform teams to deliver secure, reliable AI experiences on tight timelines.

Oversee AI-specific risk coverage - prompt injection, data leakage across users and permissions, hallucinated or ungrounded output, safety/refusal/policy compliance, and cost/latency regressions.

Ensure infrastructure-level validation - output parity for quantization, KV-cache, speculative decoding, and batching; output equivalence across serving backends and accelerators.

Invest in observability and AI-assisted tooling - metrics, logging pipelines, distributed tracing, drift monitoring, and agentic QA tooling that makes testing itself smarter and faster.

Spot problems before they occur, resolve cross-functional bottlenecks, and present your team’s work to executive leadership to advocate for resources and technical direction.

Requirements

You will stay close to architecture, design reviews, and trade-offs, and partner with ML engineers, inference/performance engineers, distributed systems teams, and platform teams across Cupertino, Seattle, and other sites. You will hire and grow engineers, shape the team’s roadmap, define quality bars where none exist yet, and represent the team to senior leadership and partners. This role requires strong technical depth, exceptional people-management skills, and the ability to navigate ambiguity in a fast-paced environment - including the inherently non-deterministic, probabilistic nature of generative output., 8+ years of experience in software and/or ML systems development, or equivalent experience.

3+ years of engineering management experience, with a proven track record of delivering complex, large-scale projects across multiple teams or organizations.

Experience architecting test, qualification, or evaluation strategy for large-scale distributed systems - ideally ML serving or inference platforms.

Hands-on background in one or more compiled languages (C, C++, Objective-C, or Swift) and proficiency in a scripting language (e.g., Python).

Self-directed: the ability to drive a strategy or project from a simple idea to production, setting clear priorities and consistently delivering on schedule with measurable outcomes.

B.S., M.S., or Ph.D. in Computer Science, Computer Engineering, Electrical Engineering, or equivalent experience.

Preferred Qualifications

Experience with machine learning and LLMs - common practical applications and frameworks (e.g., PyTorch, Hugging Face Transformers, or comparable inference/serving stacks).

Familiarity with LLM serving and inference optimization (batching, KV-cache, quantization, speculative decoding, distributed/multi-accelerator serving) and GPU-accelerated software.

Experience using AI/LLMs to improve testing itself - test-case generation, defect detection, or reducing manual QA effort.

Experience with CI/CD, Kubernetes, containers, and cloud-native systems, and integrating automated evals into release pipelines.

Experience with observability and distributed tracing for ML systems (e.g., Splunk, Prometheus, Grafana, LangSmith, or similar) and monitoring for model drift.

Experience validating agentic workflows - tool-use, function-calling, and multi-turn coherence.

Track record of hiring, developing, and retaining strong engineers, and leading change across multiple sites.

Benefits & conditions

At Apple, base pay is one part of our total compensation package and is determined within a range. This provides the opportunity to progress as you grow and develop within a role. The base pay range for this role is between $195,700 and $338,400, and your base pay will depend on your skills, qualifications, experience, and location.

Apple employees also have the opportunity to become an Apple shareholder through participation in Apple’s discretionary employee stock programs. Apple employees are eligible for discretionary restricted stock unit awards, and can purchase Apple stock at a discount if voluntarily participating in Apple’s Employee Stock Purchase Plan. You’ll also receive benefits including: Comprehensive medical and dental coverage, retirement benefits, a range of discounted products and free services, and for formal education related to advancing your career at Apple, reimbursement for certain educational expenses - including tuition. Additionally, this role might be eligible for discretionary bonuses or commission payments as well as relocation. Learn more about Apple Benefits

Note: Apple benefit, compensation and employee stock programs are subject to eligibility requirements and other terms of the applicable plan or program.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.jobmonkeyjobs.com
Prepare application

Good distractions

Loading talks and stories from around this role…