Research Engineering Intern, AI Evaluations
Karya (company site, opens in a new tab)BengaluruOn-siteDirect career pageEst. 3–6 LPA
Posted 2h ago
Reach people at Karya
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Karya you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Build, run, and maintain end-to-end evaluation pipelines for AI model assessments including dataset preparation, model inference, and annotation task management.
- Monitor and troubleshoot live evaluation processes, coordinate issue resolution with platform teams, and ensure quality control by automating data checks and anomaly flagging.
- Perform analysis on annotation data, compute evaluation metrics, and contribute to technical reports and public result releases while maintaining reproducible tooling and documentation.
Minimum Requirements
- Currently pursuing or recently completed a Bachelor's or Master's degree in Computer Science, Machine Learning, NLP, or related field.
- Strong programming skills in Python, with experience using data libraries such as pandas.
- Working knowledge of large language models (LLMs), modern machine learning, and familiarity with calling models via APIs.
- Solid foundation in probability and statistics. Work Experience Required: Not explicitly mentioned in the JD.
Ideal Candidate Profile
- Experienced with ML projects involving evaluation, annotation, or human feedback data, preferably with multilingual or Indian language NLP exposure.
- Possesses methodical debugging skills and willingness to handle operational issues across interdisciplinary teams involving engineering, research, and domain experts.
- Comfortable managing ambiguous, messy data environments with shifting priorities and takes ownership of reliable end-to-end evaluation operations.