| About This Role
Job Purpose
Since its official release in October 2019, Autify has been implemented by numerous clients, and our client base is continuing to grow. While we provide all the essential functions required in a test automation platform, we continue to receive requests for new functions and improvements. Autify is working on growing the product further by adding new features. Also, we are looking for opportunities beyond the existing Autify services. To expand our product lineup, we are looking for an AI engineer who focuses on prompt engineering to fully utilize the LLMs’ power, and building LLM-powered PoC applications in Python.
You will mainly be responsible for developing a new product utilizing machine learning techniques and generative AI from a proof of concept into a releasable product.
Responsibilities
- Create effective prompts to maximize the quality of the output from LLMs based on the product specifications
- Create PoC Web/CLI applications that use LLMs or ML under the hood to validate the feasibility of ideas
- Build our machine learning models using data relevant to the software testing if needed
- Work with other engineers, designers, and product leads to implement various features while considering performance, security, and reliability
- Proactively identify functions that can be improved, and suggest possible solutions in the technical aspects and product-related ideas
- Participate in on-call rotations for incident & alert handling
Required Qualifications
- 2+ years of technical experience with Python and 5+ years of experience in software development
- Experience in developing APIs with FastAPI and web applications
- Over a year of experience in prompting open-source and closed-source LLMs
- Has good comprehension and familiarity with CSS and HTML
- Up to date with the latest Machine Learning Research especially on LLMs and Prompt Engineering
- Experience in building metrics for evaluating various tasks LLMs
- Being able to work in Japan standard time (Working partially in JST can be discussed)
- Ability to communicate and work in English
Nice-to-Have
- Over two years of experience in training and customizing deep learning models, especially LLMs
- Knowledge of natural language processing and visual recognition
- Proficient in the process of analyzing, hypothesizing, and testing
- Experience in MLOps
- Modern development experience with Agile or Scrum
- Experience in E2E test automation with test automation frameworks like Playwright, Cypress, Selenium, Appium, and etc.
Selection Process
1. Submission of online coding test (take-home)
2. Submission of technical assignment (take-home)
3. Technical interview & HR interview: 90 mins
4. Final interview: 60 mins
Note:
- We will request to provide references after the final interview.
- The interview steps might change depending on the hiring status in our pipeline.
- We can arrange casual interviews before the coding test upon the candidate's request. (Subject to availability of both parties)
