This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Agent Engineer based in United States.
This role focuses on building and evolving an advanced AI scheduling assistant that powers next-generation construction planning workflows. You will design and implement production-grade agentic systems that combine LLM reasoning, tool use, and workflow orchestration to deliver highly reliable, high-impact user experiences. The position sits at the intersection of applied AI, backend engineering, and product development, with strong emphasis on system behavior, evaluation rigor, and real-world performance. You will own the full lifecycle of AI agent features, from architecture and prompt design to observability and continuous improvement. The environment is highly technical and collaborative, working closely with leadership and AI engineering peers to shape core product intelligence. This is a hands-on role for someone passionate about building robust, production-scale AI systems that directly influence user outcomes in complex domains.
Accountabilities:
- Design, build, and own end-to-end AI agent features, including backend systems, tool integrations, and user-facing components
- Develop and evolve agent architectures such as ReAct loops, routing systems, multi-node graphs, and control flow logic for reliable behavior
- Improve model performance through advanced prompt engineering, tool design, and optimization of latency, cost, and response quality
- Integrate and manage LLMs across multiple providers, balancing tradeoffs between accuracy, speed, and cost efficiency
- Build and maintain the MCP-based tool ecosystem connecting the agent to core scheduling and planning systems
- Design and operate evaluation frameworks including datasets, automated testing, replay systems, and performance metrics
- Implement robust observability across agent workflows using tracing, logging, and monitoring to debug and improve production behavior
- Ensure safe execution of model-generated outputs, including sandboxing, validation, and secure handling of tool interactions
- Collaborate closely with product, backend, and frontend teams to deliver fully integrated AI-driven features
Requirements:
- 4+ years of software engineering experience with recent hands-on work building production LLM or AI agent systems
- Strong proficiency in Python for building production-grade backend services
- Proven experience designing and implementing agentic systems using frameworks such as LangChain or LangGraph
- Strong prompt engineering skills with ability to debug, refine, and optimize model behavior using traces and logs
- Experience building LLM evaluation systems, including datasets, regression testing, and performance benchmarking
- Familiarity with MCP or similar tool/function-calling integration patterns for LLM applications
- Solid understanding of API design (REST, WebSockets, SSE) and distributed system communication patterns
- Strong product mindset with ability to balance technical tradeoffs and user impact
- Excellent communication skills suited for remote-first collaboration
- Preferred: experience with Go, MongoDB, Redis, AWS or GCP, Docker, CI/CD pipelines, or vector databases
- Preferred: familiarity with RAG systems, embeddings, or retrieval-augmented architectures
- Preferred: exposure to construction tech, scheduling systems, or project management domains
Benefits:
- Competitive salary with equity (stock options)
- Full benefits package supporting health and well-being
- Remote-first work environment
- Opportunity to build AI systems impacting a multi-trillion-dollar global industry
- High-growth startup environment with strong technical ownership and autonomy
- Career development and long-term growth opportunities
- Collaborative, engineering-driven culture focused on innovation and product excellence