Services

Resources

Company

Our Work

Blog

Back to Talks

From DevOps to MLOps - Scaling ML models to 2 million API requests per day

Chinmay Naik

CEO @One2N

Jun 6, 2024

Learn how to deploy and scale Machine Learning models to 2 Million+ requests/day using MLOps best practices. In this talk, you’ll learn how to go from data preparation to deployment to scaling ML models that can run at large scale - all without breaking the bank.

Continue watching

Watch Talk

Migrating a Fintech Analytics Stack to Open Source - Kshitish Deshpande - FOSS Meetup Pune

Kshitish Deshpande

Software Engineer @One2N

Migrating a fintech analytics stack off fully managed AWS services can save serious money, but only if you do it without breaking business reporting or slowing teams down. In this FOSS Meetup Pune talk, Kshitish Deshpande (Software Engineer at One2N) walks through how his team helped a cross‑border B2B fintech processing 50–70M USD in daily transactions move from an all‑AWS analytics pipeline (Postgres, DMS, Glue, Athena, QuickSight) to a fully self‑hosted open‑source stack on ClickHouse, Pebble, Prefect, and Apache Superset. You’ll see how they planned the migration, ran both pipelines in parallel, and gave business teams the same dashboards while cutting infra costs dramatically.

Watch Talk

Kubernetes for Hybrid Cloud Environments - Harshwardhan Mehrotra - #60 Kubernetes Pune Meetup

Harshwardhan Mehrotra

SRE @One2N

Scaling Kubernetes workloads across 40+ data centers is hard – especially when you must meet strict data residency and latency requirements while still leveraging the public cloud. In this talk from the Kubernetes Pune Meetup, Harshwardhan Mehrotra (Site Reliability Engineer at One2N) walks through how his team designed and operated an EKS hybrid setup for a large betting platform with data centers across the US, UK, and Europe. You’ll see how they connected on‑prem worker nodes to an AWS EKS control plane, handled networking at scale, and kept the developer experience close to a “normal” EKS cluster. What you’ll learn: - Why EKS hybrid was chosen over fully on‑prem or fully cloud, and how regulatory and latency constraints shaped the architecture. - How to design pod vs node networking, routable vs non‑routable pod networks, and when to bring in BGP. - How to connect 40+ data centers to AWS using Direct Connect / site‑to‑site VPN and Cilium/Calico CNIs. - How to expose apps using F5 and Istio/NGINX ingress when ALB is not an option. - Real‑world issues with DNS (CoreDNS, Route 53 limits, node‑local DNS) and traffic distribution, plus how they fixed them. - Lessons on egress control, firewall bottlenecks, add‑on placement (Argo CD, KEDA, Prometheus, etc.), and building repeatable playbooks for on‑prem nodes. - This talk is ideal for platform engineers, SREs, and architects running Kubernetes across data centers and cloud, or evaluating EKS hybrid for regulated workloads.

Watch Talk

Solving Synthetic Data generation using LLMs | mitramadal.ai EP2 - 2026

Chinmay Naik

CEO @One2N

In this talk at mitramandal.ai EP2, Chinmay Naik (Founder & CEO, One2N) walks through how One2N solved the problem of synthetic data generation using LLMs - covering the real-world use cases that drove it, why anonymization falls short, and how they built a tool that uses LLMs for schema generation and deterministic faker-based data generation.

Watch Talk

Migrating a Fintech Analytics Stack to Open Source - Kshitish Deshpande - FOSS Meetup Pune

Kshitish Deshpande

Software Engineer @One2N

Migrating a fintech analytics stack off fully managed AWS services can save serious money, but only if you do it without breaking business reporting or slowing teams down. In this FOSS Meetup Pune talk, Kshitish Deshpande (Software Engineer at One2N) walks through how his team helped a cross‑border B2B fintech processing 50–70M USD in daily transactions move from an all‑AWS analytics pipeline (Postgres, DMS, Glue, Athena, QuickSight) to a fully self‑hosted open‑source stack on ClickHouse, Pebble, Prefect, and Apache Superset. You’ll see how they planned the migration, ran both pipelines in parallel, and gave business teams the same dashboards while cutting infra costs dramatically.

Watch Talk

Kubernetes for Hybrid Cloud Environments - Harshwardhan Mehrotra - #60 Kubernetes Pune Meetup

Harshwardhan Mehrotra

SRE @One2N

Scaling Kubernetes workloads across 40+ data centers is hard – especially when you must meet strict data residency and latency requirements while still leveraging the public cloud. In this talk from the Kubernetes Pune Meetup, Harshwardhan Mehrotra (Site Reliability Engineer at One2N) walks through how his team designed and operated an EKS hybrid setup for a large betting platform with data centers across the US, UK, and Europe. You’ll see how they connected on‑prem worker nodes to an AWS EKS control plane, handled networking at scale, and kept the developer experience close to a “normal” EKS cluster. What you’ll learn: - Why EKS hybrid was chosen over fully on‑prem or fully cloud, and how regulatory and latency constraints shaped the architecture. - How to design pod vs node networking, routable vs non‑routable pod networks, and when to bring in BGP. - How to connect 40+ data centers to AWS using Direct Connect / site‑to‑site VPN and Cilium/Calico CNIs. - How to expose apps using F5 and Istio/NGINX ingress when ALB is not an option. - Real‑world issues with DNS (CoreDNS, Route 53 limits, node‑local DNS) and traffic distribution, plus how they fixed them. - Lessons on egress control, firewall bottlenecks, add‑on placement (Argo CD, KEDA, Prometheus, etc.), and building repeatable playbooks for on‑prem nodes. - This talk is ideal for platform engineers, SREs, and architects running Kubernetes across data centers and cloud, or evaluating EKS hybrid for regulated workloads.

Watch Talk

Solving Synthetic Data generation using LLMs | mitramadal.ai EP2 - 2026

Chinmay Naik

CEO @One2N

In this talk at mitramandal.ai EP2, Chinmay Naik (Founder & CEO, One2N) walks through how One2N solved the problem of synthetic data generation using LLMs - covering the real-world use cases that drove it, why anonymization falls short, and how they built a tool that uses LLMs for schema generation and deterministic faker-based data generation.

Watch Talk

.zshrc tmuxinator tease | Command Line Heroes EP3 - Bengaluru

Saurabh Hirani

Principal SRE @One2N

Command Line Heroes is a meetup series for developers, SREs, and terminal nerds who love living inside the shell. ​In episode 3 from Bengaluru, Saurabh Hirani (Principal SRE at One2N) walks through a real-world debugging story where Kiro CLI quietly breaks his beloved Tmuxinator setup. ​ This talk is a deep dive into how a “simple” autocomplete feature ended up sitting between Ghostty/VS Code, tmux, and zsh, and why things started to go weird: tmux panes showed commands but refused to execute them, shell startup got slower, and mysterious processes began to appear. ​ Along the way, Saurabh uses LLMs, exec, and process inspection to peel back the layers and explain what’s really happening inside your terminal sessions. CLI Heroes Ep3 was an in person meetup held on 31st Jan 2026, thanks to Smarsh Inc for providing the venue, this is just a small snippet of the things that happened at the meetup. Make sure to follow One2N events on luma to be notified of upcoming events: https://one2n.io/meetups