Senior Software Engineer – Model Training, AI Evals

Job not on LinkedIn

🕒 June 29

🇮🇳 India – Remote

⏰ Full Time

🟠 Senior

🧑‍💻 Full-stack Engineer

👻 Ghost score 44%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Chegg Inc.

WebsiteLinkedInAll Job Openings

1001 - 5000 employees

🛍️ eCommerce

📚 Education

☁️ SaaS

eCommerce • Education • SaaS

Chegg Inc. is a software development company that provides individualized learning support to students pursuing their educational journeys. Available on demand 24/7, the Chegg platform is powered by over a decade of learning insights and offers AI-powered academic support. It connects students with a vast network of subject matter experts to ensure quality learning and helps millions of students build essential academic, life, and job skills for success.

📋 Description

• Own evaluation solutions end-to-end, including methodology design, pipeline and tooling development, deployment into training and production workflows, and ongoing maintenance • Design and build evaluation frameworks and harnesses for LLMs and multi-step AI agents • Define rubrics and scoring methodologies for open-ended tasks such as tutoring quality, reasoning, and citation accuracy • Build automated model-graded and rule-based evaluators and validate them against human judgment • Develop agent-specific evaluations for tool use, multi-turn completion, planning, failure recovery, and cost/latency tradeoffs • Create golden datasets, adversarial test sets, and regression suites • Translate evaluation results into training signals for SFT/RLHF/RLAIF data curation, reward modeling, and fine-tuning priorities • Instrument production systems to collect interaction data for evaluation and training • Build dashboards and reporting on model quality trends across releases • Ensure methodological rigor through statistical significance, inter-rater reliability, sampling strategy, and resistance to metric gaming • Collaborate with Trust & Safety and Legal/Compliance on responsible-AI evaluations • Mentor engineers and establish evaluation as a core part of model development

🎯 Requirements

• 5+ years of software/ML engineering experience, including hands-on work building or maintaining evaluation, testing, or measurement infrastructure for ML systems • Direct experience with foundation model evaluation and benchmarking beyond using APIs; experience at a foundation model lab or similarly frontier research environment strongly preferred • Demonstrated ability to own an evaluation solution end-to-end, from design and dataset/methodology creation through pipeline build, deployment, and production monitoring • Direct experience designing evals for LLMs and/or AI agents • Strong programming skills in Python, PyTorch / TensorFlow, and production-grade data/ML pipelines • Hands-on knowledge of AWS, including SageMaker and Bedrock, and Databricks, including MLflow, Unity Catalog, and Delta Lake • Applied statistics knowledge, including sample size, variance, significance testing, and aggregate metric limitations • Working knowledge of LLM training and adaptation, including pretraining, SFT, RLHF/RLAIF, and DPO • Experience with agentic architectures, including tool calling, multi-step planning, memory, and orchestration frameworks • Familiarity with evaluation and observability tooling, tracing, dataset versioning, and experiment tracking • Excellent cross-functional collaboration skills • Bias toward rigor and skepticism when evaluating metrics • Bonus: post-training techniques and evaluation methodologies, model benchmarking, and data quality practices such as curation, filtering, deduplication, and quality scoring

🏖️ Benefits

• Salary and benefits per Chegg's compensation bands and the candidate's location, in accordance with applicable pay transparency requirements • Inclusive work environment • Equal opportunity employment