.png){kind=logo}
Chappidi Sasi
Mid-level Machine Learning Engineer specializing in GPU-accelerated LLM training and inference
Connect with Chappidi
Chappidi already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
ML/LLM engineer with production experience building a multi-GPU LLM inference platform using TensorRT and vLLM, achieving ~40% p95 latency reduction through batching/KV caching, quantization, and CUDA/runtime tuning. Also has end-to-end orchestration experience (Kubernetes, Airflow) and has delivered real-time fraud detection systems at Accenture in close collaboration with non-technical risk and product stakeholders.
Experience
Education
Key Strengths
- Built and deployed an optimized LLM inference pipeline (TensorRT + vLLM) for multi-GPU serving
- Reduced p95 latency ~40% and significantly increased throughput via batching, KV caching, quantization, and CUDA/runtime tuning
- Designs modular agent/RAG workflows with automated evaluation, edge-case testing, and production monitoring/feedback loops
- Production orchestration experience across Kubernetes (serving) and Airflow (training/retraining pipelines)
- Translated non-technical fraud/risk requirements into ML solutions; improved fraud detection while reducing false positives
Discover more candidates like Chappidi
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent