Tiki is extremely focusing on growing products to wider customer selection. This is not outside the goal of everything we have done, is to bring more happiness and convenience to our customer.
As a member of Supply Chain Optimization team, we have the responsibility to drive core projects to help accelerate Tiki’s effectiveness in full-filling and managing their inventory, fastening delivery speed and making right investment decision for company budget. To be honest, we have to argue that the growing of customer selection would be our new challenges - the more selection, the more challenges in managing and optimizing things.
Fortunately, our team is constantly iterating and standing together to solve problems. We found out many solution to deal with challenges. We play with Big Data, Machine Learning, and even Deep Learning.
We know the road, but we're just getting started.
We are looking for Data Scientist to stand together with us and take responsibility for building AI models to solve our problem in demand forecasting and delivery / pick path optimization. And since we are just at the beginning of the road, you can let your imagination run free. We encourage everyone to dare to try new things and even make some mistakes, after all, it is all part of life and learning.
Responsibilities for Data Scientist:
- Develop clever algorithms and pragmatic solutions to our automation and optimization problems.
- Build high accuracy machine learning models that can learn and optimize performance from vast amount of data.
- Develop metrics to measure the outcome/impact of your introduced solutions.
- Work with other members to implement and integrate into our existing systems.
- Document and improve the solutions over time.
- Evaluate and identify new technologies for implementation.
- Communicate with our business and technical teams to understand the analytics requirements.
- Respond and follow up to incorporate feedback and draw new insights.
- Prioritize tasks to meet multiple deadlines.
Why you will want to work here:
- We are constantly iterating! There is no such best proposal for anything, no fastest API, no best machine learning models. We design, build, test, ship, and optimize, and test. Just a stream of improvements and tests.
- We have data-driven mindset, every point of changes must be tested to gain insights into its impacts on key metrics. It's a long process, but over time, we gradually learn and become confident in our approach.
- We love "best practices". Serving important features with high throughput always give us a hitch to research and apply best practices. Any experiment or optimization is always welcomed.
- We are both independent and open. We own our products. Technical problems would be discussed internal, but for difficult one, we could request other's help.
- Good mathematical and statistical background.
- Good understanding of machine learning and deep learning methods; in particular, RNN and LSTM
- Strong experiences with ML/DL frameworks such as Tensorflow, Torch, etc... is a must. In particular, must be fluent in converting research papers into production-ready codes
- Some experiences of time series forecasting methods such as (S)ARIMA(X), ETS, etc is highly desired
- Working knowledge of combinatorial optimization algorithms and heuristics such as genetic algorithm, ant colony optimization, simulated annealing, etc... is also highly desired