Opportunité exclusive
We’re looking for a strong Senior Full-Stack Engineer to take an AI-powered B2B platform from a successful POC and initial pilot into a fully production-ready, scalable system.
This is a hands-on role with significant ownership. You’ll work with an existing, functioning product and lead the technical evolution required to make it ready for real production usage, larger workloads, multiple environments, and ongoing development at scale.
Transition the current platform from POC/pilot architecture to a production-grade system.
Set up Development, Staging, and Production environments.
Build and maintain Docker-based deployment and CI/CD pipelines.
Establish cloud infrastructure, managed PostgreSQL, object storage, backups, and secrets management.
Introduce reliable background job and queue architecture for long-running AI workflows.
Improve scalability, concurrency handling, resilience, and performance.
Set up monitoring, logging, error tracking, and alerting.
Strengthen application and infrastructure security.
Improve production reliability of LLM integrations, including rate limits, retries, timeouts, fallbacks, and failure handling.
Continue developing new product capabilities across frontend and backend.
Frontend: React, TypeScript, Vite, TanStack Query, Tailwind, shadcn/ui
Backend: Node.js, TypeScript, Express, tRPC, PostgreSQL, Drizzle ORM
AI: OpenAI, Anthropic, Google Gemini
Processing: PDF, DWG, and document-processing workflows
10+ years of Full-Stack and/or Backend engineering experience.
Strong hands-on experience with TypeScript and Node.js.
Solid React experience.
Strong PostgreSQL experience, including schema management and database migrations.
Hands-on Docker and Linux experience.
Experience designing and building CI/CD pipelines.
Strong experience with AWS, GCP, or Azure.
Experience setting up and operating real production environments.
Experience with queues and background workers such as Redis, BullMQ, SQS, Pub/Sub, RabbitMQ, or similar.
Strong understanding of scalability, concurrency, asynchronous processing, and distributed systems.
Experience with production monitoring, observability, error tracking, and alerting.
Strong understanding of application security, authentication, authorization, and secrets management.
Ability to take ownership of an existing codebase, understand it deeply, and make sound architectural decisions.
LLM Experience – Must Have:
Hands-on production experience integrating directly with LLM provider APIs such as OpenAI, Anthropic, Gemini, or similar.
Experience handling rate limits, retries, backoff strategies, timeouts, provider failures, and API-specific behavior.
Experience working with structured LLM outputs and production-grade API integrations.
Understanding of token usage, latency, cost management, reliability, and model limitations.
Ability to troubleshoot LLM workflows in production and distinguish model/API issues from application or infrastructure issues.
Multi-model and multi-provider LLM architectures.
Model routing and fallback strategies.
Long-running AI workflows and asynchronous AI processing.
AI systems where accuracy, consistency, and reliability are business-critical.
Terraform or other Infrastructure as Code tools.
Sentry, OpenTelemetry, Datadog, or similar observability platforms.
B2B SaaS platforms.
Document processing, PDF, CAD, or DWG workflows.
Migrating a POC or pilot-stage system into a production-grade architecture.
******** Native English required