Senior AI Backend & Orchestration Engineer

Cavendish Professionals; Polska; Remoto; PLN 260.000 - 380.000; Tempo pieno

Descrizione del lavoro

Cavendish Professionals is seeking a Senior AI Backend & Orchestration Engineer to join an enterprise AI platform team in a fully remote setup focused on Go-based low-latency systems. You will co-architect and scale orchestration engines, implement multi-agent workflows, and ensure robust, streaming-ready patterns.

Key work includes building RAG pipelines, vector DB integrations, tool-calling loops, and distributed memory management across microservices, with strong ownership and English

Competenze

• Mastery of Go (Golang) for core low-latency systems development.
• Deep familiarity with Python for AI ecosystem compatibility, tooling, and model evaluation.
• Demonstrated experience building multi-agent workflows, tool calling, and RAG architectures.
• Experience with Kubernetes or modern cloud-native container runtimes.
• Excellent English communication skills for daily international collaboration.

Mansioni

• Co-architecting, scaling, and optimizing the core orchestration engine to handle high-concurrency, heavy AI workloads, and streaming protocols with minimal latency.
• Designing and deploying stateful multi-agent frameworks, autonomous tool-calling loops, and resilient runtime error-recovery patterns.
• Building and optimizing advanced RAG pipelines, including semantic chunking, vector database integrations, and reranking mechanisms to deliver high-precision context to models.
• Designing clean, strongly-typed, extensible APIs serving as the foundation for modern WebUI and CLI developer environments.
• Handling LLM lifecycle management, token streaming architectures, and distributed memory management across asynchronous microservices.

Conoscenze

Go mastery

Python familiarity

Multi-agent workflows

Tool calling

RAG architectures

APIs design

Go concurrency

Cloud-native patterns

Strumenti

Kubernetes

Descrizione del lavoro

Senior AI Backend & Orchestration Engineer | Go (Golang), Python & Multi-Agent Workflows | Enterprise AI Platform

We are looking for an experienced Senior AI Backend & Orchestration Engineer to join our client, an in-house technology consultancy of a global consulting firm, driving next-generation cloud-native AI engineering initiatives. In this role, you will take technical co-ownership of architecting and scaling a core AI orchestration engine, focusing on extreme performance, low latency, and robust patterns for multi-agent systems and advanced retrieval pipelines.

What You’ll Be Doing:

• Co-architecting, scaling, and optimizing the core orchestration engine to handle high-concurrency, heavy AI workloads, and streaming protocols with minimal latency.
• Designing and deploying stateful multi-agent frameworks, autonomous tool-calling loops, and resilient runtime error-recovery patterns.
• Building and optimizing advanced RAG pipelines, including semantic chunking, vector database integrations, and reranking mechanisms to deliver high-precision context to models.
• Designing clean, strongly-typed, extensible APIs serving as the foundation for modern WebUI and CLI developer environments.
• Handling LLM lifecycle management, token streaming architectures, and distributed memory management across asynchronous microservices.

What We’re Looking For:

• Proven commercial track record as a Senior Backend or Systems Engineer building distributed, high-concurrency enterprise applications.
• Strong systems architecture background: deep grasp of asynchronous processing, state machines, event-driven systems, and streaming mechanisms.
• Direct hands-on experience in the AI ecosystem: orchestration concepts, vector databases, embeddings, and prompt-driven execution loops.
• Consultant mindset: ability to propose clean architectural patterns, justify engineering tradeoffs, and collaborate effectively with technical leadership and cross-functional teams.
• Strong ownership, adaptability, and focus on delivering production-grade code in fast-moving environments.

Must-Haves:

• Mastery of Go (Golang) for core low-latency systems development.
• Deep familiarity with Python for AI ecosystem compatibility, tooling, and model evaluation.
• Demonstrated experience building multi-agent workflows, tool calling, and RAG architectures.
• Experience with Kubernetes or modern cloud-native container runtimes.
• Excellent English communication skills for daily international collaboration.

Location & Working Setup:

• 100% Remote working model (Only Poland location)