// about
i liked taking things apart as a kid. remotes, toys, anything that didn't get taken away fast enough. computers were the first thing i could take apart and put back together without getting in trouble.
i study ai/ml at pes university in bengaluru. i started in research and co-authored a paper on discovering llm prompting techniques with knowledge graphs, which was accepted at icann 2026. somewhere along the way i got more curious about what sits underneath: queues, storage engines, processes that crash and come back. that's mostly what i build now.
i also ta data structures & algorithms, do competitive programming, and take quizzing more seriously than i should.
- codeforces specialist (1580)
- 430+ leetcode problems
- paper at icann 2026 (padua, italy)
- b.tech ai/ml, pes university, 2023–present
// work
jun – aug 2026 · bengaluru
summer analyst intern, wealth management technology · morgan stanley
built an ai-powered validator that checks team names against compliance policy on its own, saving legal and compliance officers weeks of manual review. optimized 10+ sql queries for internal reporting, and shipped backend changes to the team's java codebase.
learned: how to work properly inside a big collaborative team.
- java
- sql
- llms
aug 2025 – present
teaching assistant, data structures & algorithms · pes university
run labs and debugging sessions on trees, graphs, recursion and complexity, and write problem sets.
feb – apr 2025
project intern, advanced driver assistance · centre for innovation & entrepreneurship, pes university
real-time vehicle and pedestrian detection with yolov8 (85% accuracy). cut inference latency 30% by switching models based on system load. lane detection and multi-object tracking on embedded hardware.
learned: how vision models actually behave outside a notebook.
- pytorch
- opencv
- yolov8
- embedded
// projects
01mini-vllma from-scratch llm inference engine with a paged kv cache and continuous batching.engine built; no vllm comparison yetpython / pytorch / hugging face2026
personal project. engine scaffolding, benchmark harness and plots were written by an ai agent.
- paged kv cache: block pool and block table with slot mapping
- token-budget scheduler with chunked prefill and recompute preemption
- prefix cache with lru eviction; blocks are hashed after compute, so same-step requests never read unfinished blocks
- batched decode over a padded block-table gather, plus an invariant checker
- token-for-token match with hugging face generate on a tiny random qwen2 (float64, cpu and cuda)
- profiling showed per-sequence gpu copies dominated decode; each step now uses one host-to-device copy and one batched attention call per layer
- limits: small model only, no cuda graphs, no fused kernel for the paged path, prefill runs per sequence
- no comparison against real vllm yet, and no claim that it beats hugging face or static batching
- python
- pytorch
- hugging face
02distributed job queuea durable single-node job queue in c++ with sqlite storage and lease-based retries.built, not deployedc++ / sqlite / posix sockets2026
solo
// the bottleneck was fsync, not the network
- multi-threaded socket broker (a thread per connection) with sqlite storage in wal mode
- at-least-once delivery: workers claim jobs under time-limited leases
- failed jobs retry with exponential backoff; repeated failures move to a dead-letter queue
- priority scheduling
- concurrency safety comes from sqlite's file locking
- profiling showed per-commit fsync, not networking or threads, as the throughput bottleneck
- a slow query, diagnosed with explain query plan: a compound index was replaced with two partial indexes
- a stale-lease race, fixed with a fencing token in the ack/nack protocol
- c++
- sqlite
- posix sockets
03100 days of cudaa 100-day log of cuda kernels, starting from vector add.in progresscuda2026
daily practice log
- planned: vector add and reductions first
- planned: matmul from naive to coalesced to tiled shared memory, compared against cublas
- planned: fused softmax with warp reductions
- planned: a paged-kv gather kernel that reads through a block table
- no kernel results published yet
- cuda
04fault-tolerant ml training runtimea multi-process ml training runtime that survives worker crashes.finishedc++ / posix (fork/exec/waitpid) / linux2026
solo
- parallel workers across cores that keep training when one dies
- mmap'd dataset loading
- crash-safe checkpointing for fast recovery
- c++
- posix (fork/exec/waitpid)
- linux
05mini-batchera dynamic request batcher in c++, simulated on cpu.built; cpu simulation onlyc++172026
the user wrote the worker in steps 1 and 2. an ai coding agent wrote steps 3 and 4, the benchmarks, plots and docs. the starter skeleton came from a template.
- pipeline: load generator, request queue, batcher thread, batch queue, then instance threads
- batches close on a max batch size or a max queue delay
- simulated model with a fixed cost plus a per-item cost, so it runs without a gpu
- checks that completed requests equal sent requests and that every callback fires exactly once
- thread sanitizer runs show no data races
- c++17
06bustuba buffer pool manager and b+ tree index from cmu 15-445's bustub.in progress: buffer pool + b+ tree donec++2026
cmu 15-445 course project. parts of it were built with claude code sessions.
- buffer pool manager with page replacement and disk i/o
- b+ tree index with ordered lookups and range scans
- c++
07politicalsima simulated democracy where ai politicians learn to win elections, and voters push back.finishedpython / mesa / gymnasium / stable-baselines3 / networkx / tensorboard2025
solo
- ai candidates trained with reinforcement learning (ppo) shift positions across multiple policy issues to win votes
- voters live in a small-world social network and influence one another's views
- shocks like economic crises, pandemics and wars hit the electorate mid-run
- elections every 20 steps; tracks polarization and voter satisfaction over time
- python
- mesa
- gymnasium
- stable-baselines3
- networkx
- tensorboard
// publications
icann 2026, padua, italy (poster) · sep 2026 · accepted
the missing link: knowledge graph-guided discovery of novel prompt compositions
a heterogeneous knowledge graph of the prompt-engineering space, with new prompting techniques found as link prediction.
- discovered compositions beat established baselines by up to 27% on truthfulqa-mc1 and 18% on tweeteval-sentiment
// writing
writing soon. drafts are in progress.
