Romania•US
Remote
Senior
Full Time
remotecontractAILLMseniorsoftware engineering
Requirements
- •5+ years of software engineering experience with production systems 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
- •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 including model selection, routing, fallbacks, cost and rate-limit management
- •Strong Python and SQL skills, comfortable with TypeScript/Node.js
- •Solid production engineering experience on AWS including Docker, CI/CD, testing, and observability
- •Product thinking and business focus with ability to define success in measurable terms and own outcomes
- •Daily use of agentic coding tools (Claude Code, Codex, Cursor or similar) with good judgment to verify output
- •Clear communication skills with technical and non-technical stakeholders in English
What You'll Do
- •Design and build LLM agents and agentic workflows including tool use via MCP, structured outputs, retrieval (RAG), multi-step orchestration, and human review steps where needed
- •Build and maintain MCP servers and tool layers that give agents governed access to company data and systems
- •Own quality and cost management including evals and golden sets, per-agent telemetry (tokens, cost, latency, accuracy), prompt and model versioning, provider failover and model routing
- •Ship through CI/CD pipelines with tests, evals, containerized deploys, monitoring, and rollbacks
- •Contribute to shared platform components such as the agent template, LLM gateway, and observability
- •Work directly with business stakeholders to scope, prioritize and validate use cases and push back when an agent is not needed
- •Use AI coding tools daily, verify their output and catch mistakes
Nice to Have
- •Experience with LLM observability or gateway tooling such as Langfuse, LiteLLM, OpenTelemetry for LLM traces or similar
- •Experience with B2B contact and company data enrichment, deduplication, matching
- •Experience in cloud operations or FinOps including monitoring, incident handling, cost management
- •Experience with event-driven or workflow-engine technologies like Kafka, Temporal or similar
- •Experience replacing no-code or workflow-tool automations with production code
Benefits
- •Fully remote work format
- •Collaborative and creative environment valuing initiative and experimentation
- •Paid time off and sick leave
- •Reduced working hours on Fridays during the summer
- •Days off on US national holidays plus your birthday
- •Work schedule: 14 PM - 23 PM EEST (Kyiv time)
About Infuse
At the heart of INFUSE is a demand engine powered by data: first-party buying groups, deep intent signals, and exclusive competitor and market intelligence insights. This AI-driven demand engine ensures precision targeting across in-market buyer and account profiles to drive qualified interest. Omnichannel outreach and INFUSE-exclusive marketing programs identify and engage prospective buying groups throughout their journey.
Boca Raton, FL, US
1000 - 5000
Marketing & Advertising