Job Summary:
ICON is looking for a pragmatic builder who has made the leap from traditional software engineering into the emerging world of agentic AI development to join our Government Technology team. As an AI Software Engineer at ICON, you will be responsible for designing and shipping AI-powered tools, workflows, and autonomous agents that accelerate ICON's construction technology platform.
Responsibilities:
โข Design and build agentic AI systems that automate complex, multi-step workflows across ICON's software platform
โข Develop LLM-powered features and products using state-of-the-art foundation models and APIs (e.g. Anthropic, OpenAI)
โข Architect and implement multi-agent pipelines, tool-use systems, and Model Context Protocol (MCP) integrations
โข Build robust RAG systems including document ingestion, chunking strategies, embedding pipelines, and vector retrieval
โข Collaborate with software and domain teams to identify high-leverage AI automation opportunities and translate them into shipped products
โข Own the full development lifecycle of AI features: prototyping, evaluation, deployment, and iteration
โข Serve as a technical resource and informal mentor on agentic AI best practices across the engineering organization
โข Stay at the leading edge of the agentic AI landscape and bring emerging techniques into production
Qualifications:
Required:
โข 8+ years of professional software engineering experience with a strong foundation in backend or full-stack development
โข Demonstrated experience building and shipping production-grade products using LLMs and agentic frameworks
โข Proficiency in TypeScript and/or Python
โข Deep understanding of prompt engineering, context management, and LLM reasoning patterns
โข Experience with tool-use, function calling, and agent orchestration (e.g. LangChain, LlamaIndex, Claude Code, or custom implementations)
โข Proficiency in the design and execution of structured evals to measure and improve AI system performance
โข Strong communication skills and comfort working cross-functionally with both technical teams and non-technical stakeholders
โข Experience working in or alongside government, defense, or regulated environments
โข Strong experience working with code generation agents (e.g. Claude Code, Cursor, Devin-style systems)
Preferred:
โข Experience with MCP (Model Context Protocol) server development and integration
โข Familiarity with vector databases (e.g. pgvector, Pinecone, Weaviate)
โข Experience with fine-tuning, RLHF, or model evaluation pipelines
โข Strong background in ML fundamentals: embeddings, transformers, attention mechanisms
โข Exposure to structured output generation and LLM-based data extraction
โข Familiarity with AWS and serverless infrastructure for AI workloads
โข Interest or background in the AEC (architecture, engineering, construction) industry
Company:
ICON is a construction technology company that uses 3D robotics, software, and advanced materials. Founded in 2017, the company is headquartered in Austin, USA, with a team of 201-500 employees. The company is currently Growth Stage.