Team Overview: LinkedIn’s Core AI organization is dedicated to transforming the professional world through innovative solutions, including advanced models, agents, and AI systems. Our ‘HALO’ Evaluation Engineering team builds core technology that powers LinkedIn’s model and agent evaluation ecosystem. This is a horizontal and deeply cross-functional team empowering product, linguists, and operations partners to evaluate new AI solutions quickly, efficiently, and at scale. We’re building a next-generation AI evaluation and optimization platform that makes AI systems measurable, reliable, and continuously improving in production. As AI systems become more autonomous and agentic, evaluation can’t rely on manual labeling and disconnected tools. Our team is creating a unified intelligence layer that connects human feedback, AI judges, synthetic data, training pipelines, and real-time monitoring into a closed-loop improvement engine — defining how AI agents are validated, shipped, and improved at scale. Team Scope & Future Work Golden Dataset Generation Tools – Automate creation, labeling, quality control, and versioning of high-quality evaluation datasets from specs and production data. LLM-as-a-Judge Infrastructure – Build and align large model evaluators to reliably score outputs, reasoning traces, and agent behavior. Distilled In-House Evaluator Models – Convert large judges into efficient internal models for scalable, low-latency evaluation. Synthetic Data Generation – Generate controlled, edge-case, and stress-test datasets to expand coverage and robustness. Observability for AI Agents – Measure hallucinations, tool-use accuracy, reasoning quality, and convergence in real time. End-to-End Agent Evaluation Framework – Standardize offline benchmarking, regression testing, and production quality monitoring. Training Signal Pipeline (SFT & RLHF) – Turn evaluation signals and datasets into structured training data for continuous model improvement.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Manager