Senior Software Engineer (Backend/LLM Infrastructure)
NEW Gruppe
22 days ago
Role details
Contract type
Permanent contract Employment type
Full-time (> 32 hours) Working hours
Regular working hours Languages
English Experience level
SeniorJob location
Tech stack
Continuous Integration
Python
OpenID
Role-Based Access Control
Redis
Security Assertion Markup Language (SAML)
SQL Databases
SQLAlchemy
Large Language Models
Backend
FastAPI
Playwright
Kafka
Celery
Job description
- Build and maintain Python/FastAPI services, SQLAlchemy/Alembic models, Redis caching, and background jobs (Celery/RQ).
- Implement and optimize LLM orchestration pipelines: RAG flows, agent workflows, evaluation, tracing, retries, and feature flags.
- Own CI/CD pipelines, environment promotion, schema migrations, canary/blue-green deployments, and operational reliability.
- Add observability: structured logs, OpenTelemetry tracing, and RAG quality dashboards.
- Integrate secure multi-tenant access with SSO (OIDC/SAML) and RBAC.
- Participate in on-call rotations, incident response, and continuous improvement of production systems.
Requirements
-
5-8+ years of backend or full-stack engineering experience with Python/FastAPI/LangGraph in production.
-
Hands-on experience with LLM systems, embeddings, vector stores, and performance/cost optimization.
-
Strong CI/CD and operations mindset: SLOs, monitoring, incidents, and rollbacks. Solid SQL, Redis, and background job experience.
-
Experience integrating SSO (OIDC/SAML) and multi-tenant RBAC.
-
Nice addition: Playwright/Stagehands/pywinauto, Temporal/Kafka, feature flags (langfuse/Unleash), HIPAA/SOC2 exposure.
About the company
At New Objectives, we are building Europe's first secure, auditable, and EU-compliant automation infrastructure for legacy systems. We're taking a practical approach to improving how engineers work with AI systems. Combining LLMs with familiar software engineering methods to make it easier for people to build, modify and maintain software automations. Our platform lowers the effort required to turn natural-language instructions into deterministic, testable code that can interface with and automate legacy systems.