ML Engineer – Custom GPT Models
This position was filled!
Who are they?
GoodAI started as a research and development initiative inside Keen Software House in January 2014, when CEO Marek Rosa invested $10M USD into the project.
At Good AI we are focused on 3 areas
- Research of AGI
- Applied AI & Robotics
- AI Game development
Our long-term goal is to build general artificial intelligence that will automate cognitive processes in science, technology, business, and other fields. We conduct our own research, advocate fundamental AI research at the EU governmental level, and forge a community of like-minded groups through the GoodAI Grants program.
GoodAI is a company with around 30 talented people working all across the world.
GoodAI stands apart from other AI companies because of our roadmap, framework, and big-picture view. We pursue general AI with a long-term, 10+ year vision, and remain dedicated to this goal. We will not be distracted by narrow AI approaches or short-term commercialization, though we are certain to find useful applications for our general AI technology along the way.
Our roadmap, framework, and experimental implementations are at a very early stage and should be taken as works in progress. We are focused on the gradual accumulation of skills and recursive self-improvement. We do research in growing network topologies and modular networks and train and teach our AI in our School for AI.
At GoodAI, we want to create a positive future for everyone. Developing general AI will be the most helpful thing in human history, and we want to help make this dream come true.
Dominik Čech - Game designer
Job description
Are you interested in transformer based AI models and their applications in computer games? Do you have a background in Deep Learning? Would you like to push the boundaries of AI in computer games and work on artificial general intelligence?
You will have an opportunity to work on a novel game revolving around AI and large language models. Your work will range from concept creation through to implementation, testing and deployment.
Design, train and deploy custom transformer based large language models for areas such as chatbots, information extraction, sentiment analysis, language model driven behavior
Organize collection of human-curated training data
Deploy the models in the cloud
Design and evaluate model performance and accuracy metrics relevant to the game
Find creative solutions for challenges such as limited amount of data, real-time inference speed requirements and delivering models with a low cost of inference
Perform code reviews, write documentation
Present solutions
Take part in team-wide meetings and discussions
Share your knowledge with the rest of the team
Learn more about our AI game:
We offer:
Great team!
Effective development & processes not delayed by bureaucracy
Work on a product with an ambition for being novel
Opportunity to make a significant impact
Healthy work-life balance and five weeks of paid holidays
Unlimited sick days (we trust our people)
Unique working environment – Oranzerie
Remote collaboration is the norm – take home office anytime you want or work from another country
Relocation package
Competitive compensation and a generous bonus model
Stock options
Family-friendly
Team socialization – games, parties, outdoor activities, trips. Bring your family members!
Talent development and long career rewards – time dedicated for study.
Company-paid online and offline education courses, books and magazines, participation at industry conferences and workshops
Studio cafeteria with free coffee and healthy fruit days
Regular company lunches and outside grills
Team Culture
Results-oriented: we measure ourselves only by our results
**No limits: **we can achieve anything; we are pushing our limits in technology and art
Integrity: we have the courage to do the right thing, regardless of the consequences and the inconvenience
Extreme ownership: It does not matter if you are a leader or an individual contributor. Every team member accepts accountability and equal responsibility for our collaborative effort.
Excellence in execution: Our teams aim for excellence in everything we do – we get what we tolerate
Simplicity in design: less is better; avoid feature creep; simplicity is the ultimate sophistication
Teamwork: we treat our colleagues with respect, supporting each other throughout to ensure we maximize the value for everyone while creating an atmosphere of trust*
Preferred experience
Experience with transformer-based language models
Desire to create own smaller LLM models with advanced reasoning capabilities
Knowledge of both API-only models like GPT-3.5, 4, as well as open-source LLMs such as LLama, Alpaca, Vicuna, MPT, RedPajama, GPT4All and others (e.g. on HuggingFace)
Experience with fine-tuning these models and model optimizations (for inference speed / cost)
Sparsification of LLMs, Cost reduction
Knowledge of MLOps stacks such as AWS, Docker, REST APIs, scaling
Experience collaborating with other developers in an Agile environment: communication, version control, and issue tracking
Ability to learn – you learn new concepts and skills rapidly, and look to understand things in an in-depth way
Passion for games and the latest machine learning developments
Ability to read and understand machine learning related papers
Background or professional interest (coupled with good knowledge) in deep learning, language models and transformers
Drive – you’re energetic, hard-working, and persevere through adversity until the job is done, and done well. You are motivated by getting results and always aim for excellence in what you do
Communicative level of English – you will be part of an international team since our colleagues are from all over the world; you must be able to clearly explain your ideas and solutions
Friendly personality, respectful approach
Hacker Mindset – try things fast, rather do it now in a dirty but functional way then take a few months
Considered a plus:
University degree / Ph.D. in a related field (Machine Learning, Computer Science, Robotics, etc..)
Deep understanding of how language models work under the hood
Experience with tweaking transformer based architectures
Previous work experience on computer games or chatbots