Shrey_07
Remote: Yes
Willing to relocate: Yes — anywhere. India, EU, US, UK.
Technologies: Python, PyTorch, Redis LLM inference, LLM fine-tuning (Qlora, peft), Google ADK, Agentic systems, FastAPI, Playwright, Docker, SQL, AWS, Tensorflow, MLflow, MCP, RAG, Neo4j, Git/Github, CI/CD, Typescript, API, scikit-learn, Vector Databases, HuggingFace.
Resume - https://drive.google.com/file/d/1qUxHkYu8dx866aGJy4-GLejJui7...
Email: [email protected]
---
2026 CS grad looking for my first full-time role. I build things that have to actually work, and I spend most of my time on the part where they don't.
KARMA — KARMA (github.com/ShreySharma07/Multi-Agentic-CUDA-optimization): a self-improving multi-agent system that writes and tunes GPU code. Five specialized agents profile, plan, code, test and reflect, with a vector memory that carries lessons from one kernel to the next. github.com/ShreySharma07/Multi-Agentic-CUDA-optimization
Repliq — a computer-use agent that turns one narrated screen recording into a self-verifying execution plan. Runs a 20-step Salesforce workflow end to end. Same lesson, different shape: it used to report every run as a success while records silently failed to save. Fixed by giving each primitive a postcondition contract checked against real application state, not against the click returning. github.com/ShreySharma07/salesforce-agent
Currently working on developing novel technique to post-tune Gemma 4 31B model for swe tasks.
Remote: Yes
Willing to relocate: Yes (India, Europe, US)
Technologies: Python, C++, PyTorch, FastAPI, Docker, Playwright, LLM agents (ReAct, MCP, tool calling), RAG, QLoRA/PEFT, quantization, Redis, PostgreSQL, AWS
Résumé/CV: https://drive.google.com/file/d/1qUxHkYu8dx866aGJy4-GLejJui7...
Email: [email protected]
Recent CS grad. I build agent systems and the verification machinery that proves they actually worked — the second part is where most of my time goes.
KARMA (github.com/ShreySharma07/Multi-Agentic-CUDA-optimization): 5-agent pipeline where LLM agents read NVIDIA Nsight Compute traces and rewrite CUDA kernels from measured bottlenecks. 8.99x over PyTorch eager, 87.9% of theoretical peak memory bandwidth, on a 6GB consumer GPU. I got a 40x early on that turned out to be a kernel computing garbage very fast — the model was optimizing my metric, not the task. Most of the work after that was a verification harness it couldn't game: compile gate, 3-seed correctness vs PyTorch, determinism gate, interleaved benchmarking. 0% false positives across every number I report.
Repliq (github.com/ShreySharma07/salesforce-agent): autonomous computer/browser-use agent. One narrated screen recording in, self-verifying execution plan out then the agent performs the task in a secured docker environment. 20-step Salesforce workflow end to end. Dominant failure mode was steps reporting success while the record silently never saved — fixed with per-primitive postconditions checked against real application state instead of agent self-report. just connect it with your org give me the task recording and done you don't have to worry about the day to day redundant tasks.
Looking for AI/ML or backend engineering. Happy to go deep on either project.
Willing to relocate: Yes (US, Europe)
Technologies: Python, PyTorch, FastAPI, Docker, LLM agents (ReAct, MCP tool-calling, A2A protocol), RAG, async/await, PostgreSQL, AWS (SageMaker, Lambda, Step Functions, DynamoDB), speect-to-text, DeepLearning, QLora, Peft, sklearn
Résumé/CV: https://docs.google.com/document/d/153Tu_DBgt-OGOw1i607_Yj40...
Email: [email protected]
Recent CS grad building AI systems from the ground up. Built a multi-agent system that optimizes CUDA kernels using real NVIDIA Nsight Compute profiling data fed into LLM prompts (1.08x–1.31x speedup on KernelBench Level 1, 0% compile failure). Also built an autonomous AI agent platform (Repliq) that converts screen recordings with voice into executable workflows using ReAct loops, tool-calling, and zero-trust sandboxed execution, shipped it to salesforce employee for automating redundant task in salesforce. Looking for AI/ML engineering roles — happy to talk about either project in depth.
I've worked on projects involving model fine-tuning, RAG agents, and AI deployment on platforms like Hugging Face, and I’m currently diving deeper into systems-level programming and multi object tracker for autonomous vehicles.
I’d love to know if there are any internship roles that align with my background, and I’d really appreciate if you could help route me to the right person or team.
Thanks in advance!
— Shrey