Looking for a job

Karthik Kashyap HV

@karthikkashyaphv

Message

I build production LLM inference, agent systems, and GPU-serving platforms.

India

Message

What I'm looking for

I'm looking to build measurable, reproducible AI systems across LLM inference, GPU performance, agent infrastructure, applied deployment, and safety evaluation—especially where engineers can ship artifacts, benchmark rigorously, and solve real production constraints.

I'm focused on building production LLM inference, evaluation, agent infrastructure, GPU performance, safety, and applied AI delivery.

I design model-to-production systems spanning Transformers, RAG, vLLM serving, observability, Kubernetes, quantization, speculative decoding, distributed training, MCP, and mechanistic interpretability. My project direction includes LLM serving platforms, inference performance benchmarking, optimization toolkits, agent/MCP platforms, and interpretability labs.

I value measurable artifacts, reproducible benchmarks, and systems another engineer can run.

Experience

Work history, roles, and key accomplishments

HV AI Engineer

Karthik Kashyap

AI engineer focused on production LLM inference, evaluation, agent infrastructure, GPU performance, safety/alignment, and applied AI delivery. Portfolio spans model-to-production engineering from Transformer internals and RAG through vLLM serving, observability, Kubernetes, quantization, speculative decoding, distributed training, MCP, and mechanistic interpretability.