SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Ruya AI is a venture-backed defense-tech company building AI-native intelligent software for sovereign institutions operating in mission-critical environments. The company is headquartered in Massachusetts with offices across the US, Europe, and the Middle East.
The Quant team is responsible for developing multi-modal intelligence agents that surface hidden patterns across disparate data sources and generate predictive outcomes for operators. As an Artificial Intelligence Engineer, you will design and build agent systems, tool integrations, and evaluation pipelines. You'll own the orchestration layer that converts complex operator requirements into secure, reliable, and measurable AI capabilities, working hands-on in close partnership with the broader engineering team.
Core responsibilities include building asynchronous Python/TypeScript services using FastAPI, Pydantic, and asyncio; developing agent orchestration, subagent delegation, tool calling, and structured outputs; designing MCP tools and AG-UI/SSE integrations; improving prompt, context, memory, and token-management strategies; building safeguards against prompt injection, data leakage, and unsafe tool use; creating behavioral evaluations and regression datasets using Langfuse; tracing model calls and tool execution with Langfuse, Sentry, and OpenTelemetry; and diagnosing failures spanning model behavior, tools, data sources, and distributed services.
Required qualifications include strong production Python and asynchronous programming experience; experience building LLM applications with tool use and multi-step reasoning; knowledge of structured output validation and non-deterministic system testing; practical understanding of prompt injection and sensitive-data risks; and the ability to evaluate AI behavior empirically.
Preferred qualifications include experience with MCP, Langfuse, LiteLLM, Anthropic-compatible APIs, agent memory, CopilotKit, geospatial intelligence, entity graphs, fine-tuning and pre-training of LLM models, agent and memory graph engineering, RAG, and knowledge systems.
The role is based at headquarters in Massachusetts with remote arrangements available in California, Texas, Maryland, Virginia, and across the US. The company also hires at locations in Dubai, Bosnia, Croatia, and Serbia, with visa sponsorship and relocation assistance available for international positions.
