Ramachandra Sharma Chowduru

Senior Software Engineer

Bengaluru, Karnataka, India8 yrs 2 mos experience
Highly Stable

Key Highlights

  • Designed systems for 620M+ users globally.
  • Achieved 99.99%+ availability in distributed systems.
  • Led cloud migration increasing deployment frequency by 30%.
Stackforce AI infers this person is a Backend-heavy Infrastructure Engineer specializing in Distributed Systems and ML Platforms.

Contact

Skills

Core Skills

Distributed SystemsMl InfrastructurePerformance EngineeringCloud & Devops

Other Skills

C++PythonLLVMKubernetesAWS EKSDPDKONNX RuntimeOpenVINOgRPCDockerKafkaTerraformCI/CDPerformance ProfilingSoftware-Defined Networking

About

I build the infrastructure that makes real-time systems work at scale — low-latency, high-reliability software where microseconds and uptime matter. Over 8+ years at Samsung R&D, I've designed and shipped distributed systems serving 620M+ end users across 25+ global deployments at 99.9%+ availability. My current work spans ML inference frameworks with sub-10μs hard real-time decisioning, LLVM compiler passes for cache-aware struct optimization, and Kubernetes-based platform engineering that cut deployment cycles by 30%. What I specialize in: → Distributed systems design — fault-tolerant architectures, DAG-based scheduling, lock-free concurrency → Performance engineering in C/C++ — LLVM IR passes, cache-line optimization, kernel-level profiling → ML infrastructure — real-time inference pipelines (ONNX Runtime, OpenVINO), model serving, hardware-aware scheduling → Kubernetes & cloud-native platforms — EKS migration, rolling upgrades, CI/CD automation, Infrastructure as Code → Technical leadership — cross-pod architecture reviews, org-wide profiling standards, mentoring B.Tech + MS by Research (Computer Science), IIIT Hyderabad. Open to Senior/Staff Engineer roles in distributed systems, infrastructure, or ML platform engineering. 📧 ramchandra0323@gmail.com 🧰 TECH STACK Languages: C++, Python, Java, Golang, JavaScript Systems & Infrastructure: Distributed Systems, System Design, Linux Systems Programming, TCP/IP, gRPC, Concurrency & Lock-Free Data Structures, LLVM, Performance Profiling, High Availability, Observability Cloud & DevOps: Docker, Kubernetes, AWS (EKS), Infrastructure as Code, CI/CD Pipelines, REST APIs, Kafka, Redis Data & ML: PostgreSQL, MongoDB, MySQL, PyTorch, ONNX Runtime, OpenVINO 🔍 PASSIONS & PREFERENCES Solving challenges at a global scale. Open to Senior/Staff Engineer, SDE, distributed systems, or cloud backend roles. Let’s connect if you’re building distributed or performance-critical platforms!

Experience

8 yrs 2 mos
Total Experience
3 yrs 1 mo
Average Tenure
1 yr 10 mos
Current Experience

Samsung r&d institute india - bangalore private limited

Senior Software Engineer

Jul 2024Present · 1 yr 10 mos · India · On-site

  • Leading systems architecture initiatives across Samsung R&D's platform engineering org. I own the ML inference infrastructure, compiler optimization toolchain, and cloud migration strategy for a platform serving 620M+ users globally.
  • Designed an LLVM IR pass for co-access pattern analysis combined with KaHyPar hypergraph partitioning to emit
  • cacheline-aligned struct reordering, reducing cache misses by 30%, CPU utilization by 10%, and critical-path execution
  • time by 5–15% on a multicore real-time scheduler; integrated into CI/CD via a single compile flag.
  • Designed a production real-time ML inference framework with dual execution modes: hard real-time decisioning under
  • 10μs via DPDK-based zero-copy ring buffers and soft real-time async batch processing of 180+ concurrent units, with
  • pluggable backends (ONNX Runtime, OpenVINO), hot-swappable models, and automatic fallback to rule-based logic at
  • 100% inference availability SLA.
  • Identified recurring deployment bottlenecks across the organization and led migration from monolithic deployment to
  • Amazon EKS with Kubernetes rolling upgrades for near-zero-downtime releases, automated scaling, and CI/CD
  • pipelines, increasing deployment frequency by 30% and saving 200+ engineering-hours annually.
  • Directed cross-pod initiative to deliver a dual-path data processing system using software-defined networking and
  • dynamic workload slicing, reducing end-to-end latency by 30% and increasing throughput by 40%.
  • Defined org-wide performance profiling standards; led architecture reviews across pods using telemetry/KPIs, mentored
  • on optimization/concurrency, driving consensus and efficiency gains.
  • Technologies: C++, Python, LLVM, Kubernetes, AWS EKS, DPDK, ONNX Runtime, OpenVINO, gRPC, Docker, Kafka, Terraform, CI/CD
C++PythonLLVMKubernetesAWS EKSDPDK+9

Samsung r&d institute india

2 roles

Software Engineer

Jul 2018Jul 2024 · 6 yrs · Bangalore Urban, Karnataka, India · On-site

  • Built and scaled a high-performance distributed systems platform in C++, Java, and Python, serving 620M+ end users
  • across 25+ global deployments with 99.99%+ availability.
  • Designed a DAG-based task scheduling framework with lock-free queues and core pooling, improving runtime
  • performance by 20% under high-concurrency workloads.
  • Rebuilt inter-service communication from polling to event-driven ring-buffer callbacks, reducing latency by 3ms and
  • eliminating CPU waste across production modules.
  • Improved data processing throughput by 50% under noisy input conditions by implementing a redundant-signal
  • aggregation pipeline with weighted combining.
C++JavaPythonDistributed Systems

Software Engineer Internship

May 2017Jul 2017 · 2 mos · Bangalore Urban, Karnataka, India · On-site

  • Built a lock-free, FAA-based concurrent memory pool for a resource-constrained embedded runtime, achieving 20% reduction in memory overhead.
PyTorchReal-Time Operating Systems (RTOS)

Token

Software Development Intern

Jul 2015Sep 2015 · 2 mos

  • Developed a secure full-stack application with tokenization-based encryption for sensitive financial data.
Systems DesignCommunication

Esagu

Software Developer Internship

Aug 2014Nov 2014 · 3 mos · Greater Hyderabad Area · On-site

  • Built a crop advisory system with integrated payment portal under Dr. P.K. Reddy at CDE Lab, IIIT Hyderabad.
Computer GraphicsWeb Development

Education

International Institute of Information Technology Hyderabad (IIITH)

Master's degree — Computer Science

Apr 2016Apr 2018

International Institute of Information Technology Hyderabad (IIITH)

Bachelor of Technology - BTech — Computer Science

Jul 2013Apr 2017

Narayana Junior College

High School — MPC

Jan 2010Jan 2013

Ushodaya High school

10thClass (SSC)

Jan 2000Jan 2010

Stackforce found 100+ more professionals with Distributed Systems & Ml Infrastructure

Explore similar profiles based on matching skills and experience