2 months ago
Remote, United StatesMid Level
H1B sponsor
Responsibilities
- Design and build agentic AI systems that automate complex, multi-step workflows across ICON’s software platform.
- Develop LLM-powered features and products using foundation models and APIs such as Anthropic and OpenAI.
- Architect and implement multi-agent pipelines, tool-use systems, and Model Context Protocol integrations.
- Build RAG systems with document ingestion, chunking strategies, embedding pipelines, and vector retrieval.
- Collaborate with software and domain teams to identify AI automation opportunities and deliver them as products.
- Own the full development lifecycle of AI features, including prototyping, evaluation, deployment, and iteration.
- Serve as a technical resource and informal mentor on agentic AI best practices.
- Track emerging agentic AI techniques and bring them into production.
Requirements
- At least 6 years of professional software engineering experience with a strong backend or full-stack foundation.
- Demonstrated experience building and shipping production-grade products using LLMs and agentic frameworks.
- Proficiency in TypeScript and/or Python.
- Deep understanding of prompt engineering, context management, and LLM reasoning patterns.
- Experience with tool use, function calling, and agent orchestration, including frameworks such as LangChain, LlamaIndex, Claude Code, or custom implementations.
- Ability to design and execute structured evaluations to measure and improve AI system performance.
- Strong communication skills and comfort collaborating with technical teams and non-technical stakeholders.
- Must be able to obtain and maintain a security clearance.
- Preferred experience with MCP server development and integration, vector databases, fine-tuning, RLHF, model evaluation pipelines, ML fundamentals, structured output generation, LLM-based data extraction, code generation agents, AWS serverless infrastructure, and government, defense, regulated, or AEC environments.
Benefits
- Remote work is available with periodic travel to ICON headquarters in Austin, Texas as projects require.
Tech Stack
Categories
About ICON
ICON is the global leader in construction automation, developing robotics, intelligent software systems, and advanced materials that are changing the way the world builds on Earth and beyond. For more information visit www.iconbuild.com or follow on X™, Instagram®, Facebook®, YouTube®, or Threads® (@ICON3DTech).