As a Gen AI Content Evaluator, you will play a crucial role in the development and enhancement of Generative AI technologies. Your responsibilities will include evaluating and benchmarking large language models (LLMs), fine-tuning their performance, and advancing the techniques used in evaluating and measuring their effectiveness. This role offers an exciting opportunity to contribute innovative ideas and improvements to our evaluation processes and benchmarks.
Key Responsibilities
- Model Evaluation. Assess and benchmark the performance of Generative AI models, including fine-tuning and optimizing their capabilities to ensure high-quality outcomes.
- Automated Evaluation Pipeline. Contribute to the development and enhancement of automated evaluation pipelines and metrics to streamline and improve the assessment process.
- Innovation. Propose and implement new evaluation techniques and criteria to advance the state-of-the-art in Generative AI.
- Collaboration. Work closely with remote teams to integrate evaluation findings into the broader AI development process and collaborate on improving overall model performance.
- Communication. Clearly articulate evaluation results and insights to stakeholders, providing actionable recommendations for model improvements.
Required Technical and Professional Expertise
- Experience. Minimum of 3 years of industry experience in programming, particularly with Java.
- Skills. Strong communication and collaboration skills with proven ability to work effectively with remote teams.
- Technical Proficiency. Demonstrated experience with Generative AI technologies and an understanding of their applications and evaluation.
Preferred Technical and Professional Expertise
- Methodologies. Exposure to Agile methodology, enhancing your ability to adapt and thrive in a dynamic environment.
- Tools. Familiarity with AI/ML frameworks and tools relevant to Generative AI evaluation.
About Business Unit
IBM Software integrates intelligence into core business operations, from machine learning to generative AI, helping organizations become more responsive, productive, and resilient. Our software solutions are designed to leverage data, optimize AI impact, and provide comprehensive support for businesses in the hybrid cloud era. We are committed to using our technology to create significant value and drive transformation.
Your Life @ IBM
At IBM, we foster an environment of growth, innovation, and support. Our culture encourages you to be curious, embrace challenges, and contribute to meaningful advancements. You’ll have opportunities to develop your career, experiment with new ideas, and work alongside a team that values diverse perspectives and collaborative problem-solving.
Why Join Us?
- Innovation. Work on groundbreaking technologies and be at the forefront of AI and mainframe integration.
- Growth. Continuous learning and career development opportunities within a global technology leader.
- Diversity. Be part of an inclusive environment where every individual’s contributions are valued and respected.
COVID-19 Vaccination Requirement:
Please note that this job requires you to be fully COVID-19 vaccinated prior to your start date. Proof of vaccination status will be required. If you are unable to be vaccinated for medical or religious reasons, please let us know during the onboarding process.
Location Statement
When applying, consider roles that align with your experience and expertise. Our recruiters recommend applying to a maximum of 3 roles per year for the best candidate experience.
Being You @ IBM
IBM is committed to diversity and inclusion and is proud to be an equal-opportunity employer. We consider all qualified applicants regardless of race, color, religion, sex, gender identity, sexual orientation, national origin, disability, age, veteran status, or other characteristics.
Apply Now.If you are ready to lead in the AI space and contribute to transformative projects, we invite you to apply for the Gen AI Content Evaluator role at IBM. Join us and be a part of a team dedicated to making a difference through technology.