Senior AI Engineer

Chordian's core AI systems are built and in production. Enterprise customers run them under real SLAs in their own cloud environments. We need engineers who can take production AI systems to the next order of magnitude.

What you will work on

Agent-to-agent memory protocols

Own and evolve the layer that lets agents read, write, and maintain coherent memory across multi-agent enterprise deployments.

Retrieval agent architecture

Own the fusion layer, latency budget, and reasoning loop as query complexity grows.

LLM orchestration and extraction

Maintain extraction quality, model routing, and structured output at growing ingest scale.

Entity Coherence systems

Extend accuracy and performance for entity identity across the full memory.

What we are looking for

Required

• 5+ years production backend engineering with throughput and latency you have owned
• Shipped LLM applications in production — multi-turn agents, retrieval pipelines, eval harnesses
• Python plus Go, Rust, or TypeScript
• Retrieval infrastructure in production contexts
• Observability, deployment, cost management, incident response

Strongly preferred

• Agent-to-agent communication patterns and MCP protocol work
• BYOC, on-premises, or regulated cloud deployments
• Entity resolution or knowledge management at scale

Not a fit if

• Demos and wrappers but not production systems with real SLAs
• Prefer well-defined specs to open-ended ownership