Location: Anywhere in the World Permanent Remote (Europe Latam Asia )
Contract length 6 Months
Opportunity Full Time 8 hours
MustHave:
Total Years Of exp 4 years experience mandatory
Mandatory Skills: Rust min 3 yrs CI/CD min 3 yrs Git min 3 yrs
About the Role
We are seeking a proficient Rust Developer with a strong interest in machine learning and humancomputer interaction to join our team. In this role you will contribute to the development and refinement of large language models (LLMs) by participating in Reinforcement Learning from Human Feedback (RLHF) tasks. Your work will involve building tools to facilitate human feedback as well as directly providing insights to guide the training and improvement of LLMs
Key Responsibilities:
- Participate in RLHF tasks by providing human feedback on LLM outputs helping to guide model training.
- Evaluate the responses generated by LLMs identifying areas where the model needs improvement and providing qualitative feedback.
- Work closely with data scientists and ML engineers to ensure that feedback is accurately reflected in the model s learning process.
- Collaborate with crossfunctional teams to understand the requirements for human feedback in the RLHF process.
- Provide insights into how human feedback can be systematically incorporated into model training and improvement.
- Document processes and best practices for providing and integrating human feedback in LLM training.
- Stay informed about the latest advancements in reinforcement learning LLMs and humancomputer interaction.
- Experiment with new methods and tools to improve the collection and integration of human feedback in RLHF tasks.
Requirements:
Technical Skills:
- 3 years of experience in Rust development with a solid understanding of systems programming performance optimization and concurrency.
- Familiarity with machine learning concepts particularly reinforcement learning is highly desirable.
- Experience with humancomputer interaction user feedback systems or similar domains is a plus.
- Proficiency with version control systems (e.g. Git) and CI/CD pipelines.
- Analytical Skills:
- Strong problemsolving skills with the ability to analyze and improve the efficiency of RLHF tasks.
- Experience in evaluating and providing constructive feedback on AI/ML outputs.
git,reinforcement learning,reinforcement,machine learning,analytical skills,version control systems,problem-solving,ai/ml,concurrency,problem-solving skills,ci,rust,ci/cd,user feedback systems,performance optimization,ci/cd pipelines,cd,systems programming,human-computer interaction,learning