Senior Backend Engineer

Senior Backend Engineer- AI Simulations Platform
Location Fully remote
Start ASAP
The opportunity
We are supporting a fast-growing AI platform company with teams in the US and Berlin as it builds a new engineering group responsible for the infrastructure used to simulate and evaluate AI-powered conversations.
The platform runs large volumes of automated conversations against AI agents to test behaviour, identify regressions and generate insight into how those systems perform. You will help build the distributed services that orchestrate simulations, execute evaluation workflows and process the resulting event data.
What you will do
Design and build the distributed infrastructure behind large-scale AI conversation simulations.
Develop services that orchestrate concurrent simulation and evaluation workflows.
Build reliable, event-driven systems capable of processing high volumes of asynchronous workloads.
Design for retries, idempotency, failure recovery, backpressure, rate limiting and graceful degradation.
Integrate AI agents, LLM providers and evaluation services into production workflows.
Build APIs and internal platform capabilities used by other engineering teams.
Own services from initial design through implementation, deployment, observability and production support.
Establish testing, benchmarking and performance-validation practices for systems operating under significant concurrency.
Work closely with product and engineering stakeholders to turn emerging requirements into practical technical solutions.
Contribute to architectural decisions while remaining highly involved in coding and delivery.
What we are looking for
Senior-level software engineering experience.
A strong track record building and operating distributed, event-driven production systems.
Deep understanding of concurrency, asynchronous processing and high-throughput backend services.
Experience with messaging or streaming technologies such as Kafka, NATS, RabbitMQ, SQS or equivalent.
Strong backend engineering experience in Python, TypeScript, Go or JVM-based technologies.
Evidence of end-to-end ownership of production services.
Experience applying resilience patterns including retries, idempotency, circuit breakers, rate limiting and fault isolation.
Strong API and service-design fundamentals.
Experience with cloud infrastructure, containers and Kubernetes.
A pragmatic product-engineering mindset and the ability to work autonomously in a remote team.
Particularly relevant experience
Python backend development.
AI-agent, LLM or conversational-AI infrastructure.
Simulation, evaluation, benchmarking or regression-testing platforms.
Multi-provider LLM routing, tool orchestration or agent workflows.
Real-time systems, streaming APIs, WebSockets or server-sent events.
Azure and Kubernetes-based production environments.e.
Technology environment
Python and TypeScript · event-driven and asynchronous architecture · Kafka or NATS-style messaging · APIs and real-time services · Kubernetes · Azure · LLM and AI-agent integrations · modern observability and automated testing
You do not need to match every technology exactly. Engineers from Go, Java, Kotlin, Scala or another strong backend environment will be considered where they can demonstrate comparable experience building large-scale distributed systems and the ability to work across the existing stack.
If interested, please apply here via linkedin.

Work arrangement
Yes