Time since we first saw it
Day 16
Similar jobs usually come down between day 7 and day 76.
From 6,398 similar postings that came down. Coming down is not always a hire.
Lahore, Punjab, Pakistan
Live, first seen by us 16 days agoWork setup in the employer’s posting: On-siteFrom the employer’s posting
Employment type in the employer’s posting: Full timeFrom the employer’s posting
Build and maintain the listing-to-SKU mapping engine with confidence thresholds and review queues
Develop an image-based model to identify car make, model, year and trim for listings without usable text
Manage the local pricing algorithm, run experiments and report accuracy and bias results
Productionise models as scheduled pipelines with monitoring, retraining and data quality checks
Build and maintain data pipelines from the warehouse, scrapers, catalog and backoffice
Build and maintain the listing-to-SKU mapping engine: rules, text matching and classifiers, with confidence thresholds and human review queues.
Develop an image-based car identification model (make, model, year, generation, and trim) for listings with no usable text.
Manage the local pricing algorithm, monitor performance, run experiments, improve accuracy and reduce bias, and report results.
Productionise models as scheduled pipelines with monitoring, retraining and data quality checks.
Build and maintain data pipelines from the data warehouse, scrapers, the catalog and the backoffice.
These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.
Day 16
Similar jobs usually come down between day 7 and day 76.
From 6,398 similar postings that came down. Coming down is not always a hire.
2 open jobs
Open jobs by the week we first saw them, last 12 weeks.
Hiring recordAdd your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.
Build, run and maintain the ML infrastructure behind Kavak UAE's pricing: automated mapping of market listings to catalog SKUs, pricing algorithm, and other ML models that improve pricing accuracy, strategy and margin. Turn manual, person-dependent processes into reliable systems that are measured and retrained regularly. Key Responsibilities: Build and maintain the listing-to-SKU mapping engine: rules, text matching and classifiers, with confidence thresholds and human review queues. Develop an image-based car identification model (make, model, year, generation, and trim) for listings with no usable text. Manage the local pricing algorithm, monitor performance, run experiments, improve accuracy and reduce bias, and report results. Design backtests, holdout sets and audit samples to measure accuracy, and report it by segment. Productionise models as scheduled pipelines with monitoring, retraining and data quality checks. Build and maintain data pipelines from the data warehouse, scrapers, the catalog and the backoffice. Build supporting models for pricing strategy: depreciation and km curves, price elasticity, days-to-sell and demand. Turn reviewer feedback and manual overrides into training data and rules with expiry dates. Document models, assumptions and results clearly for non-technical stakeholders. Work with the Pricing, Data, Product and global teams on data access, deployment and priorities. Requirements Skills & Qualifications: 3–5 years in ML engineering or applied data science, with at least two models taken to production. Background in e-commerce, marketplaces, automotive, fintech or any pricing/valuation domain. Experience with tabular models (pricing, regression, classification) and with text and image data. Bachelor's degree in Computer Science, Data Science, Statistics, Mathematics, Engineering or a related field. A Master's in Machine Learning or Data Science is preferred. Technical Skills Python ML stack: pandas, scikit-learn, XGBoost/LightGBM, plus PyTorch or TensorFlow. SQL and data: strong SQL on BigQuery, Databricks or a similar cloud warehouse. Pricing models: regression and quantile regression for price ranges, plus prediction intervals. Text matching and entity resolution: normalisation, fuzzy matching, tokenisation and embeddings, used to match listings to catalog SKUs. Statistics and evaluation: holdout and backtest design, calibration, confidence intervals and A/B testing. MLOps: Docker, scheduled pipelines (Airflow or similar), experiment tracking and model registry (MLflow or Weights & Biases), monitoring and retraining. Data quality: automated validation of incoming data (Great Expectations or similar). Engineering practice: Git on GitLab with CI/CD, code review and tests. Cloud: GCP or AWS. Computer vision: fine-grained image classification, transfer learning and image embeddings. Experience with vision-language models. LLMs and vector search: extracting structured fields from listing text with LLMs, and embedding matching with FAISS or a vector database. Pricing analytics: price elasticity, and survival analysis for days-to-sell. Human-in-the-loop: labelling tools (Label Studio, CVAT) and active learning to cut manual review. Model serving: REST APIs with FastAPI. Web scraping: Scrapy or Playwright, handling site layout changes and respecting each site's terms of use. Reporting: dashboards in Looker Studio, Streamlit or Databricks. Nice to have Google Cloud Professional Machine Learning Engineer, or AWS Certified Machine Learning Engineer - Associate. (Preferred) DeepLearning.AI specialisations. (Preferred) Arabic Language Do you want to be part of this story? Apply now!
Complete your application on kavak.zohorecruit.com. The employer’s form will show what is required.
Already applied? Track this application
New ML Engineer postings at the employers we follow are down 4% over the last 6 weeks compared with the 6 before.
Each bar is one week of new postings. The darkest bars are the last 6 weeks.
Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.
We file this job under ML Engineer, by the work the posting describes.
ML engineers put machine learning models into products. They write the code that trains, ships, serves and monitors models so a recommendation or prediction works for real users.
Postings ask for strong Python and software engineering, a framework such as PyTorch, cloud services, and more and more often experience with large language models.
A data scientist often works out which model to build; an ML engineer makes it run reliably in production.
The government has no code for ML engineers, so these figures are for the closest group, computer and information research scientists.
Source: US Bureau of Labor Statistics, Occupational Employment and Wage Statistics (May 2025) and Employment Projections (2025 to 2035). Occupation code 15-1221.
Selected passages from the saved posting. Check the full description for conditions and exceptions.
No pay amount identified in the saved description.
Lahore, Punjab, Pakistan
Working pattern and location restrictions need checking in the full posting.
No clear work-authorization passage found. Eligibility is unconfirmed.