Internships
AI Engineering Intern — Evaluation & LLMOps
Work on the reliability layer around AI systems: eval datasets, groundedness checks, prompt tracking, and regression tests.
Location
India / Global Remote
Workplace
Remote
Type
Unpaid internship
Team
Internships
Experience
3rd or final-year CS/Data Science
Compensation
Unpaid internship
Learning track
Learn the discipline that keeps AI useful after launch.
Ydhya sells production AI work, so evaluation is not a side task. It is how teams know whether a workflow can be trusted.
You will help create test cases, inspect failures, compare model responses, and organize evidence for senior engineers to act on.
What you will do
01
Create small evaluation datasets from anonymized workflow examples and expected answers
02
Run prompt and retrieval tests, record failures, and summarize patterns
03
Assist with groundedness, latency, cost, and regression checks
04
Maintain clear experiment notes across model, prompt, and dataset changes
What we are looking for
01
Currently in 3rd or final year of a Computer Science, Data Science, AI, or related degree
02
Comfortable with Python, notebooks, spreadsheets, and basic data analysis
03
Basic understanding of LLMs, evaluation metrics, or model testing
04
Interest in LLMOps, monitoring, governance, and AI reliability
Apply
Send a clear note about what you have shipped.
Include the role, your resume, and links to work that show your judgment. Short, concrete notes are better than generic cover letters.