Job Details

JETLYN is looking for a Senior ML Engineer to develop AI harness/runtime layer for LLM agents. Salary from 220,000 to 310,000 rubles per month. Remote position for Russian citizens.

— Develop AI harness / runtime layer for launching and managing LLM agents. — Integrate and optimize SOTA LLM in production. — Work with orchestration frameworks, including Multica, Paperclip, Symphony. — Connect and support SOTA skills & plugins, including RTK, GitNexus, and others. — Develop Python services and libraries for tool calling, execution pipelines, memory/context handling, logging, evaluation. — Build observability, guardrails, reliability, and secure execution of AI agents. — Integrate AI components with internal systems and Exchange platforms.

— Strong Python background: backend development, API integrations, asynchronous programming, testing, production practices. — Mandatory knowledge of SOTA LLM: modern models, tool/function calling, reasoning workflows, context management, cost/quality trade-offs. — Practical experience with agent orchestration frameworks, including Multica, Paperclip, Symphony. — Knowledge of SOTA skills & plugins, including RTK, GitNexus, and other modern tool ecosystems. — Experience creating production-grade AI/LLM systems. — Understanding of reliability, observability, security, and evaluation for AI solutions. — Ability to write clean, maintainable, and reliable code. Nice to have: — Experience with LLMOps / MLOps / platform engineering. — Experience creating AI SDK, agent platforms, or execution layers. — Experience with Kubernetes, CI/CD, observability stack. — Experience in fintech or high-load enterprise environments.

— Employment type: TK/IP — Salary: 220,000 to 310,000 rubles net per month.