AI Engineer

Ruya AI; California; Hybrid; USD 160,000 - 230,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

Commuter benefits

Relocation assistance

Paid time off; location-based

Job summary

Ruya AI, a defense-tech company, is expanding its engineering team in the US to build an AI-native multi-modal intel agent. You will own the orchestration layer, connect complex operator requirements to secure, reliable AI capabilities, and work hands-on with the broader engineering team.

You will design and implement agent systems, tooling integrations, and evaluation pipelines to surface hidden patterns, generate predictive outcomes, and ensure robust behavior in high-stakes environments.

Qualifications

• 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.
• Ability to evaluate AI behavior empirically rather than relying on demonstrations.

Responsibilities

• Build asynchronous Python/TypeScript services with FastAPI, Pydantic, and asyncio.
• Develop agent orchestration, subagent delegation, tool calling, and structured outputs.
• Design MCP tools and AG-UI/SSE integrations.
• Improve prompt, context, memory, and token-management strategies.
• Build safeguards against prompt injection, data leakage, and unsafe tool use.
• Create behavioral evals and regression datasets using Langfuse.
• Trace model calls and tool execution with Langfuse, Sentry, and OpenTelemetry.
• Diagnose failures spanning model behavior, tools, data sources, and distributed services.

Skills

Production Python

Asynchronous programming

LLM applications

Tool use

Empirical AI evaluation

Tools

Langfuse

MCP

Langchain-style tools

Anthropic-compatible APIs

CopilotKit

Job description

Ruya AI is a venture-backed defense-tech company building AI-native intelligent software for sovereign institutions and their affiliated organizations operating in mission-critical, high-stakes environments. Headquartered in Massachusetts (US), with offices across the U.S., Europe, and the Middle East, we are expanding our engineering team with people who demonstrate strong ownership, sound judgment, and the ability to turn complex requirements into reliable products.

The Role

Quant is the team responsible for our multi-modal intelligence agent. Our software is built to surface hidden patterns across disparate data sources, and generate predictive outcomes for the operators who rely on it. As part of this team, you’ll design and build the agent systems, tool integrations, and evaluation pipelines behind those capabilities.

You’ll own the orchestration layer that ties those systems together, converting complex operator requirements into secure, reliable, and measurable AI capabilities. You’ll work hands-on, building and operating these systems in close partnership with the broader engineering team.

If you’re excited about building autonomous agent systems that operate reliably in mission-critical environments, this is the right role for you.

Core Responsibilities

• Build asynchronous Python/TypeScript services with FastAPI, Pydantic, and asyncio.
• Develop agent orchestration, subagent delegation, tool calling, and structured outputs.
• Design MCP tools and AG-UI/SSE integrations.
• Improve prompt, context, memory, and token-management strategies.
• Build safeguards against prompt injection, data leakage, and unsafe tool use.
• Create behavioral evals and regression datasets using Langfuse.
• Trace model calls and tool execution with Langfuse, Sentry, and OpenTelemetry.
• Diagnose failures spanning model behavior, tools, data sources, and distributed services.

Required Qualifications

• 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.
• Ability to evaluate AI behavior empirically rather than relying on demonstrations.

Preferred Qualifications

Experience with MCP, Langfuse, LiteLLM, Anthropic-compatible APIs, agent memory, CopilotKit, geospatial intelligence, or entity graphs. Equivalent model and orchestration platforms are welcome.

• Fine-tuning and pre-training of LLM models
• Post-training
• Agent and memory graph engineering
• RAG and knowledge systems

Location

In the US, this role is based at our headquarters in Massachusetts, where much of the work takes place. Remote arrangements are also available in California, Texas, Maryland, Virginia and across the US.

We also hire at our locations in Dubai (UAE), Bosnia, Croatia, and Serbia. Visa sponsorship and relocation assistance are available for our UAE and European locations.

Salary and Benefits

The salary range for this role is highly competitive and benchmarked to market. Total compensation may also include equity through Ruya AI’s employee stock ownership plan (ESOP), a sign-on bonus, and other incentives over time. Final compensation reflects each candidate’s qualifications, experience, skills, certifications, and work location. All offers are contingent on a satisfactory background check and, where applicable, a reference check.

Our benefits are designed to support the health and wellbeing of every Ruyan. We regularly review and refine our offerings based on employee feedback. Below are some of the benefits and perks available to Ruya AI employees:

• Employees (and their eligible dependents) can enroll in medical, dental, and vision insurance
• Commuter benefits
• Relocation assistance
• Paid time off built into the end of each year (subject to team and business needs) and based on location
• A supportive leave-of-absence program, including time off for military service and medical events

Life at Ruya

Growth at Ruya AI isn’t tied to a fixed ladder. We pay attention to what each Ruyan is good at and where they want to go, and we shape roles and opportunities around that. Health and wellbeing benefits are part of this investment, though specifics can vary by region.

We work primarily from our offices because in-person collaboration produces better outcomes, and most teams offer one or two remote days a week. A small number of roles are remote‑eligible on an exception basis; employees in those roles must be based in the state where they’re employed, and roles marked onsite require working from an office.

Ruya AI is proud to be an equal opportunity workplace and is an affirmative action employer. We are committed toequal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, marital status, disability, gender identity or Veteran status. If you have a disability or special need that requires accommodation, please let us know.