About the role
Taskly is hiring a Machine Learning Engineer (also called an ML Engineer, or a Data Scientist on ranking) to decide who sees what in a two-sided marketplace. When a poster describes a task, the right Taskers should hear about it first. The poster should then see the offers most likely to end in a job done well.
You will own ranking end to end, working with the founder and the engineers who build the Tasker feed and the offer screens. The team is small and fully remote, so you will choose your own tools and defend them in writing. Within six months, we want a ranking model running behind an experiment. Its metric should show whether posters hire faster and Taskers get work that fits them.
What you’ll do
- Design and ship the model that decides which Taskers see a new task. Balance skill fit, distance, response history and fairness to newer Taskers with no track record yet.
- Rank the offers a poster compares, using price, reviews, response time and fit to the task. Test each change to the ordering with an A/B experiment.
- Improve search relevance for tasks and Taskers by combining keyword and vector search over Postgres with pgvector, and measure it on real queries.
- Build fraud and abuse signals, such as duplicate accounts, attempts to move a conversation off Taskly and unusual offer patterns. A human reviewer should be able to understand and act on each one.
- Define offline metrics and online experiments before you build, and write down plainly when a model change did not help.
- Handle cold start for new Taskers and new cities, where there is little history. Use priors from similar categories or neighborhoods.
- Take models from notebook to production: feature pipelines, serving behind an API, monitoring for drift and a safe way to roll back.
What you’ll need
- 4+ years of applied machine learning, with at least one ranking, recommendation, search or fraud system that you built and ran in production.
- Strong Python and SQL, and fluency in PyTorch, scikit-learn or gradient boosting libraries such as XGBoost or LightGBM.
- Practical experience with learning-to-rank and the metrics that go with it: NDCG, MRR and precision at k.
- You have designed and read A/B tests, and you know how small samples, novelty effects and interference between users mislead.
- You can serve your own model behind an API, in Python or TypeScript, and watch its behavior once it is live.
- You can explain why a model ranked something first to a non-specialist in plain language, without hiding behind jargon.
Education: A degree in computer science, statistics, mathematics or a related field is welcome but not required; ranking systems you have shipped matter more.
Nice to have
- Experience at a marketplace (Airbnb, Uber, Urban Company, Swiggy, Airtasker, TaskRabbit, Upwork) or another two-sided product.
- Cold-start methods such as bandits, exploration and priors borrowed from similar cities or categories.
- Embeddings and vector search with pgvector, including hybrid keyword and semantic ranking.
- Work on fairness or explainability in ranking, so new Taskers get a real chance at their first job.
Skills and tools
- Python
- SQL
- PyTorch
- scikit-learn
- XGBoost
- Learning to Rank
- Recommender Systems
- Search Relevance
- A/B Testing
- Feature Engineering
- pgvector
- MLOps
- PostgreSQL
Where you’ll work
- Remote. Fully remote. Open to people who live and can legally work in India, the United States, Canada or the United Arab Emirates. You work from your own country, so there is no relocation and no visa to arrange.
- Shared hours. The team overlaps for two hours each weekday: 8:30–10:30 am Eastern · afternoon in Dubai, evening in India. The rest of your day is yours to arrange.
How we hire
- 1Apply in about five minutes: your resume and a few questions
- 2A 45-minute conversation with the person you’d work beside
- 3One paid day on a real problem
- 4A decision in writing, with the reason
A person replies to every application within ten working days, even if it’s a no.
About Taskly
Taskly is a marketplace for getting anything done. Someone posts a task in their own words — typed, spoken or as a photo — and people who have been reviewed and approved send offers at a firm price. They pick one, and it gets done: a TV mounted, a website built, a parent taught to use their phone. We’re live in Canada and India and opening to more countries, built by a small team that works remotely across India, the US, Canada and the UAE.
Questions about this role
Straight answers to what people ask most.
Is the Machine Learning Engineer role remote?
Yes, fully remote. You can work from India, the United States, Canada or the United Arab Emirates, and the team overlaps for two hours each weekday: 8:30–10:30 am Eastern · afternoon in Dubai, evening in India.
How much experience do I need?
About 4+ years. It’s a guide, not a cut-off: if you can do the work described here, apply.
What does the Machine Learning Engineer role pay?
Pay isn’t listed here yet. It depends on the country you work from and your experience, and it’s discussed openly in your first conversation.
How do I apply?
Upload your resume on the application page and answer a few short questions. It takes about five minutes, with no cover letter and no account. A person replies within ten working days, yes or no.
What does the hiring process look like?
A 45-minute conversation with the person you’d work beside, then one paid day on a real problem, then a decision in writing, with the reason.
Do I need marketplace experience?
No, though it helps. Ranking, recommendation or fraud work in any product with two sides is the closest match, and you will learn the Taskly specifics on the job.
Something else? Ask it in your application. A person reads it and answers within ten working days.
We don’t use AI to screen, score or rank applications: a person reads every one. If you upload a resume, AI reads it only to pre-fill your form, and you check every field before you send.
Taskly is an equal opportunity employer. We welcome people of every background, gender, age, religion, disability, sexual orientation and nationality, and we don’t ask about any of them. If anything about the process doesn’t work for you, tell us in your application and we’ll change it.
Apply for Machine Learning Engineer
Your resume and a few questions. About five minutes, no cover letter, no account.
Apply now →