Senior Backend Engineer

Location: NO Middle East, Russia, Belarus, Ukraine, North Korea.
Contract: 1 year

About the role

We’re hiring a backend-first engineer to build and operate the systems that put Generative AI into production for document + drawing understanding (text and image). This role focuses on designing scalable microservices, APIs and inference pipelines that call foundation models (today: Bedrock on AWS) and make those model capabilities reliable and production-ready.

What you’ll own

• Design and implement backend microservices and APIs that integrate with foundation models to serve inference for document + drawing processing.
• Build scalable request-routing, caching and queuing strategies for inference traffic (handling spikes and bursty workloads).
• Implement service-level CI/CD and observability for inference pipelines (logging, metrics, alerting).
• Deploy and operate services in Kubernetes (deployments, rollouts, health checks); cluster administration is provided by platform/SRE.
• Integrate with AWS services and ensure correct IAM/least-privilege for service-to-service access.
• Collaborate with data scientists / ML engineers (they own model training; you own production integration).
• Help shape operational practices for production inference (on-call scope to be clarified; expected to support service-level incident response).

Must-have (core requirements)

• 5+ years building production backend systems / APIs in Python.
• Strong experience designing and operating distributed microservices (scalability, routing, caching, failure modes).
• Hands-on AWS experience and practical experience integrating external model APIs (today we primarily call foundation models via Bedrock).
• Production experience deploying services to Kubernetes (you deploy and operate apps there; platform team manages cluster infra).
• CI/CD experience (GitHub Actions familiarity required).
• Solid practical understanding of IAM and basic cloud security principles (least privilege, service roles).
• Demonstrable experience with logging/observability (structured logs, metrics, traces) and designing pipelines for downstream analysis.
• Terraform or other IaC experience.
• Clear, verifiable communication — ability to explain system design decisions and past work concretely.

Preferred (nice-to-have)

• Prior exposure to GenAI / LLM integrations (Bedrock, API routing, model selection)
• Experience with image/document processing pipelines (OCR, image preprocessing, parsing technical drawings)
• Experience with inference orchestration patterns (async workers, batching, GPU orchestration) or familiarity with GPU-based workloads
• Familiarity with ML lifecycle tools (MLflow, model registries, experiment tracking)
• Experience with real-time and batch inference services, feature stores, or production SageMaker usage