15 Aug
|
Weekday AI (YC W21)
|
Bengaluru
15 Aug
Weekday AI (YC W21)
Bengaluru
This role is for one of Weekday's clients
Salary range: Rs 5000000 - Rs 9000000 (ie INR 50 - 90 LPA)
Min Experience: 1+ years
Location: Bengaluru
JobType: full-time
We are looking for a highly motivated
Senior Research Engineer
with
1-8 years of experience
to join our research and engineering team. The ideal candidate will work at the intersection of
LLM research, model evaluation, and large-scale experimentation
, helping develop rigorous methods to understand, measure, and improve the capabilities of up-to-date language models.
You will design and implement evaluation frameworks, build high-quality datasets and test suites, analyze model behavior, and translate research findings into practical improvements. This role is ideal for someone who enjoys solving open-ended research problems while also being comfortable building production-quality systems.
Requirements
Key Responsibilities
- Design, develop, and maintain comprehensive LLM evaluation (evals) frameworks to measure model capabilities, reliability, reasoning, instruction following, safety, and task performance
- Conduct research on large language models, including model behavior, capabilities, limitations, prompting, fine-tuning, and evaluation methodologies
- Develop novel evaluation methodologies and experiments for emerging LLM capabilities and use cases
- Create high-quality evaluation datasets, test cases, rubrics, and automated evaluation pipelines
- Analyze model outputs using quantitative and qualitative methods to identify performance gaps and behavioral patterns
- Design controlled experiments to compare models, prompts, training approaches, and inference strategies
- Build scalable tooling for running evaluations across large numbers of prompts, models, and datasets
- Collaborate with researchers, ML engineers, and product teams to convert research insights into measurable model improvements
- Investigate failures and edge cases and develop targeted evaluations to capture previously undetected m
📌 Senior Research Engineer (Bengaluru)
🏢 Weekday AI (YC W21)
📍 Bengaluru