Nirnay Korde

Software Engineer

New Delhi, Delhi, India1 yr 11 mos experience

AI EnabledAI ML Practitioner

Key Highlights

Expert in Kubernetes-native infrastructure and AI platforms.
Proven track record in building reliable production-grade services.
Strong focus on security and operational clarity.

Stackforce AI infers this person is a SaaS and AI infrastructure engineer with expertise in Kubernetes and backend systems.

Contact

Skills

Core Skills

KubernetesInfrastructure EngineeringObservabilityCapacity ManagementSecurityBackend SystemsData PipelinesCloud EngineeringAi Platforms

Other Skills

Python (Programming Language)Go (Programming Language)DjangoFlaskDockerSystems DesignDistributed SystemsMySQLContinuous Integration and Continuous Delivery (CI/CD)GitlabYAMLRust (Programming Language)SQLiteHelmREST APIs

About

I’m a software engineer working on Kubernetes-native infrastructure and managed AI platforms, with a focus on turning complex backend systems into reliable, production-grade services. My work spans platform engineering, backend systems, and infrastructure tooling — including capacity management, observability, data pipelines, access control, and security. I’ve helped design and ship customer-facing capabilities on top of large Kubernetes environments, where correctness, governance, and operational clarity matter as much as performance. I care deeply about: Building systems that behave predictably in production Replacing fragile, ad-hoc workflows with policy-driven, auditable platforms Choosing the right level of abstraction so systems are both powerful and maintainable I enjoy working close to real constraints — cost, scale, reliability, and security — and collaborating across product, infra, and operations to ship things that last. Currently focused on platform and infrastructure engineering in cloud and AI systems.

Experience

1 yr 11 mos

Total Experience

1 yr 11 mos

Average Tenure

1 yr 11 mos

Current Experience

E2e cloud

3 roles

Software Engineer

Promoted

Jun 2025 – Present · 1 yr · Delhi, India · On-site

Designed and shipped a unified customer and internal alerting system using modern observability tooling, converting raw infrastructure signals into actionable service-level incidents.
Implemented alert deduplication, throttling, and lifecycle tracking to prevent notification noise while maintaining accurate incident state across user interfaces and downstream systems.
Delivered policy-driven scheduling for mixed Spot and on-demand capacity, preserving cost semantics in production while improving overall cluster utilization and placement reliability.
Led an enterprise authorization redesign by enforcing role-based access control over sensitive infrastructure operations and introducing governance and traceability for large Kubernetes environments.

Python (Programming Language)Go (Programming Language)KubernetesInfrastructure Engineering

Associate Software Engineer

Jul 2024 – Jun 2025 · 11 mos · Delhi, India · On-site

Redesigned GPU inventory management to stay tightly synced with Kubernetes (node/SKU-aware capacity with near real-time updates), replacing fragile counter-based availability and improving placement reliability for multi-GPU workloads.
Built a customer-facing dataset migration workflow (multi-cloud → internal object storage) using a Source → Destination → Connection model with backend orchestration to support large dataset syncs across providers.
Shipped a managed RAG (Retrieval-Augmented Generation) service by integrating an open-source RAG engine with internal inference APIs; delivered knowledge base and document lifecycle APIs, ingestion pipelines, retrieval/chat endpoints, and usage metering hooks.
Replaced a resource-heavy Kubernetes watcher with a Go-based validating admission webhook using an allow-first design, asynchronous queueing, and metrics, significantly reducing API server load and operational risk.
Automated notebook image validation with Makefile-driven build and test workflows to reduce manual verification and speed up safe rollouts; cut notebook image onboarding and validation time by ~80%.
Delivered encryption-at-rest for Ceph-backed persistent storage using an HA Vault setup. Introduced encrypted StorageClasses and rolled out encrypted PVC support at scale (1000+ database workloads).

Python (Programming Language)DjangoKubernetesBackend Systems

Software Engineer Intern

Jan 2024 – Jun 2024 · 5 mos · Delhi, India · On-site

I actively contributed to the development of a Kubernetes-based AI infrastructure platform, focusing on production readiness and operational reliability.
Improved managed services by validating stateful deployments and translating Helm configurations into workflows.
Integrated provisioning support in a Python/Flask microservice to automate Kubernetes manifest generation.
Authored extensive user and operator documentation to streamline support and maintenance processes.

Python (Programming Language)FlaskKubernetesInfrastructure Engineering