Senior AI Engineer (Remote, Contract)

Role overview We are hiring a Senior AI Engineer on a remote contract basis to design, build, and run LLM-powered agents and AI features in production. The role spans the full lifecycle, from scoping use cases with stakeholders through architecture, development, deployment, evaluation, and ongoing improvement. You will think like a product owner: understand the business problem, define success in measurable terms, ship to real users, and own the result after launch.

Responsibilities - Design and build LLM agents and agentic workflows, including tool use via MCP, structured outputs, retrieval-augmented generation (RAG), multi-step orchestration, and human review steps. - Build and maintain MCP servers and tool layers that give agents governed access to company data and systems. - Own quality and cost across agents through evals and golden sets, per-agent telemetry (tokens, cost, latency, accuracy), prompt and model versioning, provider failover, and model routing. - Ship through CI/CD with tests and evals in the pipeline, containerized deploys, monitoring, and rollbacks. - Contribute to shared platform pieces including the agent template, the LLM gateway, and observability tooling. - Work directly with business stakeholders to scope, prioritize, and validate use cases, pushing back when an agent is not the right solution. - Use AI coding tools daily, verifying output and catching mistakes.

Requirements - 5+ years of software engineering experience with production systems you have designed, shipped, and supported. - Proven experience building LLM-based agents or agentic workflows that reached production with real users. - Hands-on experience with agent frameworks and SDKs such as Claude Agent SDK, Claude Managed Agents, Pydantic AI, LangGraph, or similar, plus the ability to explain what you would build without one. - Hands-on experience with MCP and RAG, including building MCP servers or equivalent tool layers and retrieval pipelines over real, messy data. - Experience with multiple LLM providers and AWS Bedrock: model selection, routing, fallbacks, and cost or rate-limit management. - Strong Python and SQL, with comfort in TypeScript and Node.js. - Solid production engineering on AWS using Docker, CI/CD, testing, and observability. - Product thinking and a business focus, with the ability to define success in measurable terms and own outcomes. - Daily use of agentic coding tools (Claude Code, Codex, Cursor, or similar) with the judgment to verify what they produce. - Clear communication with technical and non-technical stakeholders in English.

Nice to have - LLM observability or gateway tooling experience such as Langfuse, LiteLLM, or OpenTelemetry for LLM traces. - B2B contact and company data experience in enrichment, deduplication, or matching. - Cloud operations or FinOps, including monitoring, incident handling, and cost management. - Event-driven or workflow-engine experience with Kafka, Temporal, or similar. - Experience replacing no-code or workflow-tool automations with production code.

Benefits and work setup - Fully remote work format with a schedule of 14:00 to 23:00 EEST (Kyiv time). - Collaborative and creative environment that values initiative and experimentation. - Paid time off and sick leave, reduced working hours on Fridays during summer, and days off on US national holidays plus your birthday.