WorkSendler.ai
Sendler.ai
I joined Sendler.ai in 2024 as a senior full-stack engineer on its sales-workflow automation, then became founding engineer and engineering lead of its AI LinkedIn-outreach platform, built with the founders from early customer conversations to a spec, a roadmap and a production system.
- Role
- Founding Engineer & Engineering Lead
- Period
- Aug 2024 – Aug 2026
- Where
- Sweden, remote
- Product
- AI sales automation · multi-tenant SaaS
- ARR within two months of launch
- $240K
- ARR within two months of launch
- automated actions per day
- 1M+
- automated actions per day
- automations per day through an in-house queue
- 200K+
- automations per day through an in-house queue
- engineers led and mentored
- 5
- engineers led and mentored
- Next.js apptoNestJS services
- MCP servertoNestJS services
- Public APItoNestJS services
- NestJS servicestoMongoDB
- NestJS servicestoTemporal
- TemporaltoWorkers
- WorkerstoLLM layer
- NestJS servicesto.NET AI service
- .NET AI servicetoLLM layer
Key decisions
Queues first, Temporal when the sequences grew
Automation started on BullMQ and Redis. As volume passed a million actions a day and campaigns became multi-step sequences, I led the move to Temporal so every run is durable, retryable and observable instead of state scattered across job handlers.
One provider layer, not one SDK per model
LLM-personalised messages, reply classification and agentic workflows all go through one provider layer across OpenAI, Anthropic Claude and Azure OpenAI, so a model can be swapped without touching product code.
Build the queue in-house
For the sales-workflow automation I designed a Python queue system that scaled processing to more than 200,000 automations a day, behind FastAPI and Express services with Prisma on MySQL.
Move clouds without stopping customers
The platform ran on AWS (EC2, RDS, Aurora, S3, Lambda, SQS). I planned and led its migration to Azure Functions and Service Bus while customers kept running.
Open the product to AI assistants
An MCP server exposes platform tools to AI assistants, so users can run campaigns, search leads and manage conversations in natural language, alongside a public REST API, webhooks and n8n integrations.
Meter usage per account
Credit-based usage metering and per-account rate limits keep LLM costs predictable and protect customers' accounts.
Outcome
$240K ARR within two months of launch, more than a million automated actions a day on Azure (AKS and Container Apps), and a team of five engineers I led through design sessions, code reviews and written architecture docs. Before that, working directly with the founders and enterprise clients, I helped grow the business to $180K ARR with 30+ features and a full UI redesign. I was also the technical point of contact for enterprise GTM teams at Sony Sweden and Revolut.
Go deeper
Stack
- Next.js
- React
- TypeScript
- Tailwind CSS
- shadcn/ui
- TanStack Query
- Zustand
- Redux Toolkit
- NestJS
- Node.js
- Express
- Python
- FastAPI
- C#/.NET
- LangChain
- OpenAI
- Claude
- Azure OpenAI
- MCP
- Temporal
- BullMQ
- MongoDB
- PostgreSQL
- MySQL
- Prisma
- Redis
- Socket.io
- Docker
- AKS
- Azure
- Azure Functions
- Service Bus
- AWS
- Vercel
- Vitest
- Jest
- React Testing Library
- Playwright
- Cypress
- Sentry
- PostHog