Senior AI Engineer

PLAY, GROW and WIN

To be a part of Virtuos means to be a creator.  

At Virtuos, we harness the latest technologies to make games better and more immersive than ever before. That is why we pride ourselves in constantly pushing the boundaries of possibility since our founding in 2004. 

Virtuosi is a team of experts – people who have come together to share their mutual passion for making and playing games. People with the same enthusiasm for exploring new ideas and the constant drive to excel in their field. People who believe in earning success through dedication.

At Virtuos, we are at the forefront of gaming, creating exciting new experiences daily. Join us to Play, Grow and Win – together.

ABOUT THE POSITION

We are looking for a Senior AI Engineer to help design and deliver agentic AI systems that power R&D tooling for video game asset pipelines and production workflows. You will help shape the technical direction of our internal agent platform and drive engineering practices around agent loops, memory, evaluation, and safe deployment of LLM-driven applications.
This is a senior, hands-on individual contributor role: you will write code, help design the agentic architecture, and partner with stakeholders across studios to turn emerging AI capabilities into production-grade tools.
 

Agent platform
- Build core parts of our **internal agent libraries** — abstractions that let teams build agents quickly and consistently.
- Help shape the **central agent runtime** architecture: deployment, registry, monitoring, and governance.
- Evolve the agent loop/harness (prompt orchestration, tool invocation, sub-agent delegation) and adapt open-source patterns to our use cases.
Agent loop & harness engineering
- Drive prompting at scale: system prompts, guardrails, context poisoning mitigation, and hyperparameter tuning (context window, temperature, top-k).
- Design agent tool interfaces (MCP servers, structured I/O, sub-agent composition) with built-in observability and telemetry.
- Evaluate and integrate **local LLMs** where latency, cost, or data-residency requires it.
Agent memory
- Build key parts of the shared memory layer: conversation history, context chaining, and episodic memory.
- Define short-term vs. long-term memory boundaries (decay/retention) and apply RBAC and tenant isolation for safe multi-team sharing.
Test- and eval-driven development
- Build eval harnesses and CI gates: golden traces, regression evals, offline/online metrics, and red-team prompts.
- Uphold evals as the unit of progress — no agent change ships without a measurable signal.
Backend & platform foundations
- Build scalable Python (FastAPI) services and secure APIs with relational and non-relational data modeling.
- Enforce RBAC, input validation, and error handling; implement caching, queues, and vector storage as workloads require.
Quality, delivery & collaboration
- Drive performance tuning, code reviews, and technical documentation within your area of the platform.
- Maintain CI/CD (Git/GitLab, Docker) and partner with cross-functional stakeholders (UI/UX, production, SRE, IT, game teams) to deliver agentic solutions.

Foundation (must-have software-engineering baseline)
- 3+ years of professional experience building production applications, with recent depth in AI/LLM-based systems.
- Strong proficiency in at least one of Python, TypeScript, or JavaScript - Python expertise is required for our stack (FastAPI, Pydantic, SQLAlchemy or equivalent).
- Solid database skills across relational (PostgreSQL) and non-relational systems (e.g. MongoDB, vector databases); familiar with caching/queues (Redis) where applicable.
- Working knowledge of RBAC, authn/authz patterns, and secure API design.
- Comfortable with Git, GitLab CI/CD, and Docker/containers.
- Proven testing mindset and experience with automated test suites (e.g. pytest).
Agent loop / harness engineering
- Demonstrated experience designing and operating agent loops in production - not just prompt-tuning a chatbot.
- Deep, practical understanding of prompting: guardrails, context poisoning/pollution, and the hyperparameters that govern model behavior (context window size, lost-in-the-middle effects, temperature, top-k).
- Hands-on experience integrating tools into agents: MCP, structured I/O for context, and sub-agent orchestration.
- Experience with any agent development framework - e.g. LangChain, LangGraph, Claude Agent SDK, Pydantic AI, or comparable - is acceptable.
- Strong instincts for observability and telemetry in non-deterministic systems.
Agent memory
- Practical experience implementing memory for agents: history compaction, context chaining, episodic memory, and short-term vs long-term separation.
- Familiarity with retention/decay strategies and applying RBAC to multi-tenant memory.
Evaluation & quality
- Experience with test- and eval-driven development for LLM systems: building eval sets, regression suites, and CI gates around model/prompt changes.
Communication
- **English communication is a MUST** - strong written and verbal English is required, and fluency is a significant plus given our globally distributed teams.
- Comfortable communicating technical decisions and tradeoffs across cross-functional stakeholders.
Nice to have
- Experience running **local LLMs** (e.g. via vLLM, Ollama, llama.cpp) and reasoning about the cost/latency/quality tradeoffs vs hosted models.
- Contributions to or familiarity with open-source agent harnesses (e.g. OpenCode, OpenClaw, etc).
- Experience with agent development frameworks (LangChain/LangGraph/Claude Agent SDK/Pydantic AI) beyond prototype stage.