Laxmi Narasimha Hari Yelesetty Lead AI Engineer  ·  LLM Systems & Production GenAI  ·  GCP · Azure · GPU Infra
ylnharimailme@gmail.com
+91 99161 12881
linkedin.com/in/ylnhari
github.com/ylnhari  ·  ylnhari.github.io
LLM & GenAI
vLLMLoRA/QLoRA UnslothPEFT HF Accelerate Self-hosted LLM Ops RAGLLM Eval
ML / DL / GPU
PyTorchTensorFlow RAPIDS (cuDF/CuPy) CUDA NVIDIA Morpheus Scikit-learn CV & NLP Anomaly Detection
MLOps & Cloud
GCP Vertex AIGKE Azure ML KubernetesHelm IstioDocker MLflowKubeflow GrafanaPrometheus Cloud BuildGitHub Actions
Certifications
Oracle CloudGenAI Certified Professional
MicrosoftAzure AI Engineer Associate
MicrosoftAzure Data Scientist Associate
MicrosoftPower BI Data Analyst Associate
CourseraNeural Networks & Deep Learning
Education
B.E. Electrical & Electronics Andhra University · 2012–2016 · 80%

10+ years building AI systems end-to-end — from fine-tuning to production traffic. Built a LoRA fine-tuning → vLLM pipeline that saved $300K, powering fraud detection and personalization at 40k+ transactions/sec. GPU-accelerated cybersecurity ML on NVIDIA DGX (8×A100) — behavioral anomaly detection over billion-row RAPIDS datasets, phishing classification at 2× throughput, and abuse-inbox triage at 2× the prior pipeline's case volume, each threat routed to the right security team. Delivered $2.5M in annual savings via an Azure ML quality-prediction system and optimized last-mile logistics with OR-Tools. Across 10 years and six companies, I've earned the top performance rating at every one.

Experience
Lead Artificial Intelligence Engineer
Best Buy  ·  Bengaluru, India
Jul 2025 – Present
  • Built config-driven LoRA fine-tuning framework (Unsloth + PEFT, multi-GPU via HF Accelerate → vLLM on GKE with HPA + Istio), saving $300K via self-hosted open-source LLMs; YAML-driven task addition with zero Python changes.
  • Productionalizing GenAI pipelines on GCP (Vertex AI, GKE, GCS, Cloud Build) for retail search, personalization, fraud detection, and cybersecurity at 40k+ transactions/sec.
  • Established Prometheus/Grafana/GMP PodMonitoring observability for all LLM serving infrastructure; defined AI engineering standards across teams.
ML Lead Engineer — MLOps & Engineering
Wipro  ·  US Retail Client
Aug 2023 – Jul 2025
  • Built behavioral anomaly detection on NVIDIA DGX (8×A100) with NVIDIA Morpheus — trained unsupervised autoencoder models per AWS account/user/service to fingerprint normal activity and surface threats in real time; billion-row log datasets per training run.
  • Built phishing detection (NVIDIA Morpheus) at 2,400 emails/sec (2× throughput) and automated abuse-inbox triage handling 2× the prior pipeline's case volume, auto-routing each threat to the right team; designed RAPIDS (cuDF/CuPy) GPU feature engineering across all cybersecurity workloads.
Application Dev Team Lead — Data Science / Azure ML
Accenture
May 2021 – Aug 2023
  • Azure ML quality prediction pipeline (BamaGruppen, Norway) — $2.5M saved, 130 → 160 inspected/day, +17% detection; OR-Tools Vehicle Routing optimization with significant annual logistics cost savings; supply chain hub simulation framework.
Earlier Experience
Data Scientist GD Research Centre May 2020 – May 2021 Time-series forecasting system across Consumer Goods, Oil & Gas, Power, Retail, Finance intelligence centers.
Deep Learning Engineer Tata Consultancy Services Jul 2019 – Mar 2020 Hybrid cloud + on-prem CV for semiconductor defect classification (DenseNet, transfer learning); deployed at Amkor, South Korea.
Sr. Software Engineer — ML Infosys May 2016 – Jul 2019 ML-powered Lead Conversion Prediction and Business Intelligence applications using Microsoft BI tools.