Senior AI Platform Engineer - Sovereign AI Engineering

Description:

At Dream, we redefine cyber defense vision by combining AI and human expertise to create products that protect nations and critical infrastructure. This is more than a job; it’s a Dream job. Dream is where we tackle real-world challenges, redefine AI and security, and make the digital world safer. Let’s build something extraordinary together.

Dream's AI cybersecurity platform applies a new, out-of-the-ordinary, multi-layered approach, covering endless and evolving security challenges across the entire infrastructure of the most critical and sensitive networks. Built as part of a broader sovereign AI platform, our technology is designed to operate in on-premise, private cloud, and air-gapped environments, enabling nations to maintain full control over their data, infrastructure, and AI capabilities. Central to Dream's proprietary Cyber Language Models are innovative technologies that provide contextual intelligence for the future of cybersecurity.

At Dream, our talented team, driven by passion, expertise, and innovative minds, inspires us daily. We are not just dreamers, we are dream-makers.

It starts with you - an engineer driven to build the agentic AI platform that turns LLMs into reliable, production-grade capabilities. You care about clean APIs, well-defined service boundaries, and systems that teams can build on with confidence. Dream is AI-first across the board - every team builds and operates agents. You'll architect and ship the platform that makes this possible: agent orchestration frameworks, LLM gateways, evaluation pipelines, tool-calling infrastructure, and retrieval systems. Without this platform, agents don't ship - you own the layer that turns AI research into Sovereign AI products, deployed across cloud and on-prem environments.

If you want to make a meaningful impact, join Dream's mission and build the agentic AI platform that drives Sovereign AI products - this role is for you.

• Design and build agentic systems - single and multi-agent workflows with planning, memory, context engineering, and tool use - for both internal automation and product-facing autonomous capabilities operating over long time horizons.
• Build and operate the AI platform layer - LLM gateways, prompt management, structured output handling, tool-calling infrastructure, and cost/latency optimization - deployed on Kubernetes, consumed by every team for their agentic work.
• Own the agent framework layer - orchestration primitives, execution environments, state management, and sandboxed tool execution - giving every team at Dream the building blocks to create and operate their own agents.
• Build evaluation infrastructure that gives teams confidence in agent behavior - automated LLM and agent evals for quality, correctness, safety, latency, cost, and regressions, including human-in-the-loop oversight for mission-critical workflows.
• Productionize and harden backend services (APIs, gRPC, async workers) that integrate LLMs - with proper error handling, retries, circuit breakers, and high-availability patterns.
• Own RAG pipelines and retrieval systems - indexing, chunking, embedding, vector database management, filtering, and relevance tuning for production retrieval.
• Optimize performance and cost across the AI stack - model routing, caching, batching, and inference cost management.
• Ship shared tooling - libraries, SDKs, agent templates, and documentation - while working closely with ML Platform, Data Platform, DevOps, and other teams across the Applied AI Engineering group. Own architecture, documentation, and operations end-to-end.