ML Lead Engineer (AI / LLM, Gaming Industry)

Job Description

• Design LLM system architecture (RAG, multi-agent setups, tool-calling, memory).
• Scale and optimize vector and semantic search (pgvector, hybrid search, reranking).
• Build pipelines for processing and validating GDDs (Game Design Documents).
• Develop prompt engineering, evaluation, and guardrails strategies.
• Integrate local and cloud LLMs (Ollama / OpenAI-compatible APIs).
• Architect fault-tolerant AI systems for production workloads.
• Implement monitoring for model quality, latency, and cost.
• Design multi-agent workflows and manage agent coordination.
• Prepare the platform for automated TypeScript code generation.
• Conduct code reviews, mentor engineers, and drive the team’s technical growth.

Requirements

Experience

• 6+ years of software engineering experience.
• 3+ years working on ML / Applied AI / LLM projects.
• Leadership experience (Tech Lead / ML Lead / Team Lead).

Must-have

• Deep expertise in Python.
• Hands-on experience with LLMs, RAG, embeddings, and vector search.
• Proven ability to design and support production AI/ML systems.
• Solid understanding of multi-agent architectures and LLM orchestration.
• Experience with PostgreSQL + pgvector (or similar vector database solutions).
• Experience building asynchronous and event-driven pipelines.
• Docker (production usage).
• Strong architectural thinking and a high sense of ownership.
• Ukrainian/Russian language.

Nice-to-have:

• HuggingFace / vLLM / OpenAI / Ollama
• Hybrid search, rerankers, long-context strategies
• RabbitMQ / Redis
• CI/CD and MLOps practices
• TypeScript (basic understanding)
• Experience in game dev or content generation
• Confluence / Jira API integrations

Benefits

• Competitive salary.
• 20 vacation days and 5 sick days yearly.
• A friendly and creative atmosphere.
• Opportunities for professional growth and development.
• Flexible working hours and remote work options.