I like picking apart systems that don't work as well as they should — figuring out where the bottleneck actually is, and building something that fixes it. So far that's led me to healthcare, maritime routing, judicial scheduling, satellite communications, and NLP. The domains look unrelated until you realize the job is always the same: find the structure, optimize around it, measure whether it helped.
Undergrad in Computer Engineering at Thapar Institute of Engineering & Technology. Looking for graduate programs where I can do more of this with better tools and sharper people around me.
NLP — competed in SemEval @ ACL 2026 (top-20 globally). Interested in evaluation, semantics, and taking language models into domains where they haven't been stress-tested yet.
Optimization — I keep ending up here regardless of the domain. Test suite minimization, voyage scheduling, resource allocation, communication networks. If there's a search space, I probably want to poke at it.
Structured & temporal data — graphs, time-series, brain signals. The kind of data where your choice of architecture is already a scientific claim.
Agents & systems — equally interested in models that score well on benchmarks and systems that actually do things end-to-end.
- Published & under-review work at top-tier venues (software testing, AI/NLP)
- SemEval @ ACL 2026 — top-20 system globally, system description paper submitted
- Multiple hackathon wins at national-level challenges
- Merit Scholarship (₹5.2L) for academic performance
- Open-source contributor — GSSoC '24
GSSoC(24) Badges
GitHub Stats
lakksh.sharma@gmail.com