Working Student - LLM Quantization & Inference Performance
Boost your chances at Tensordyne
Tailor your resume to this exact job and generate a matching cover letter in about 60 seconds with JobEase — our AI application assistant.
- ATS-optimized resume
- Personalized cover letter
- Match score & keyword gaps
Free to start · no card required
Get more other jobs in your inbox
Verified daily — no ghost listings.
About This Role
Working student role focused on LLM quantization and inference performance at Tensordyne. Responsibilities include evaluating low-precision model quality, researching post-training quantization, building reproducible evaluation tooling, and measuring runtime performance. The role requires current enrollment in a relevant master's program, strong Python/PyTorch skills, and an experimental mindset. The position offers mentorship, hands-on experience with cutting-edge AI inference systems, and comprehensive benefits.
Key ResponsibilitiesAI-extracted
- 1Evaluate model quality impact of low-precision computation on coding and reasoning benchmarks.
- 2Research and compare post-training quantization methods to improve inference efficiency while preserving task accuracy.
- 3Build reproducible evaluation tooling to automate experiments, track configurations, and share results with engineers.
- 4Measure runtime performance, characterizing latency, throughput, and memory usage under various deployment scenarios.
- 5Diagnose where quantization has the greatest impact on model performance.
RequirementsAI-extracted
- Current enrollment in a master's program in Computer Science, Mathematics, Electrical Engineering, Machine Learning, or a related field.
- Strong Python and PyTorch skills, including the ability to understand and modify model implementations.
- Effective use of AI coding tools and critical review of their output.
- Experimental mindset capable of formulating hypotheses, designing comparisons, and drawing conclusions from noisy results.
- Clear communication skills for presenting experimental findings and technical tradeoffs to the team.
- Typically: experience with quantization, LLM evaluation, performance profiling, or inference optimization.
Perks & BenefitsAI-extracted
Apply to This Job in Minutes
Generate ATS-optimized resume + cover letter + interview prep with Jobease.ca AI. Complete your application faster.
75% of AI Resumes Get Rejected
Beat the ATS with Jobease.ca's AI Resume Builder. Optimized for real hiring systems.
Build My ResumeProfile Match
Loading…Checking your profile against this job…
Job Overview
Share This Job
Track All Your Applications
Never lose track again. Jobease.ca organizes every application, interview, and follow-up.
Organize My Search