Forward Deployed AI Engineer

• Work directly with clients and technical leads to understand workflows, technical challenges, user needs, and opportunities for applying AI.
• Translate business, mission, and user requirements into technical designs, prototypes, and working solutions.
• Design, prototype, test, and deploy generative AI and agentic AI applications in enterprise environments.
• Build AI solutions using large language models, APIs, developer tooling, enterprise data, and modern application development practices.
• Develop agentic solutions incorporating Model Context Protocol (MCP), agent-to-agent (A2A) communication, retrieval-augmented generation (RAG), tool use, structured outputs, context management, orchestration, and human-in-the-loop patterns.
• Participate in client discovery sessions, technical working sessions, demonstrations, and solution design discussions.
• Gather feedback from users and stakeholders and rapidly incorporate that feedback into working solutions.
• Troubleshoot technical issues and collaborate with client and delivery teams to identify practical solutions.
• Explore emerging AI technologies and identify innovative ways to apply them to real-world business and mission problems.

• Build and maintain integrations with enterprise systems, services, APIs, databases, data sources, and workflow tools.
• Develop AI applications and agents that interact with enterprise data, tools, systems, APIs, and other agents.
• Build MCP-based integrations connecting AI applications and agents with tools, services, enterprise systems, and data sources.
• Implement A2A and multi-agent patterns supporting communication and coordination among specialized agents.
• Build RAG solutions, including knowledge retrieval, embeddings, vector search, grounding, and integration with enterprise content and data.
• Develop agentic workflows using tool use, structured outputs, context management, orchestration, and human review where appropriate.
• Apply modern software engineering practices to develop reliable, maintainable, testable, and well-documented solutions.
• Work with relational databases, vector stores, APIs, and other data storage and retrieval technologies.
• Support testing, evaluation, logging, monitoring, and troubleshooting of AI-enabled applications and agentic workflows.
• Participate in code reviews, technical design reviews, and other engineering quality practices.

• Communicate effectively with technical and non-technical client stakeholders.
• Ask effective questions to understand client problems, workflows, constraints, and desired outcomes.
• Explain technical concepts, prototypes, and solution approaches clearly to client stakeholders.
• Participate in client demonstrations, technical discovery, and working sessions.
• Work effectively in environments where requirements may be ambiguous, evolving, or initially undefined.
• Apply creative and analytical thinking to break complex problems into manageable technical solutions.
• Rapidly evaluate new technologies, patterns, and approaches and determine how they may apply to client needs.
• Collaborate with senior engineers and client stakeholders to evaluate technical options, risks, and trade-offs.
• Incorporate client and user feedback into solution design and implementation.

• Work with senior Forward Deployed Engineers and technical leads to develop strong FDE skills and delivery practices.
• Apply FDE best practices related to discovery, problem decomposition, requirements translation, rapid prototyping, solution design, implementation, testing, demonstrations, and knowledge transfer.
• Participate in pair programming, code reviews, architecture discussions, and technical learning activities.
• Contribute reusable code, technical patterns, accelerators, documentation, and lessons learned to improve future implementations.
• Share knowledge with other engineers and contribute to a collaborative engineering culture.
• Demonstrate curiosity and a willingness to rapidly learn new AI technologies, engineering patterns, client domains, and business processes.

• Must be able to OBTAIN and MAINTAIN a Federal PUBLIC TRUST; candidates must obtain approved adjudication of their PUBLIC TRUST prior to onboarding with Guidehouse. Candidates with an ACTIVE PUBLIC TRUST or SUITABILITY are preferred.
• THREE (3+) or more years of overall work experience.
• Experience in software engineering, AI/ML engineering, data engineering, solution engineering, or a related technical role.
• Experience performing forward deployed engineering or comparable client-facing technical delivery, including working directly with users or clients to translate business or mission needs into working technical solutions.
• Hands-on experience building generative AI, large language model, or agentic AI solutions.
• Hands-on experience developing solutions using Claude APIs, Claude for Enterprise, Claude Code, tool use, Custom Skills, or comparable enterprise large language model platforms and developer tooling.
• Hands-on experience with Model Context Protocol (MCP) and its use in connecting AI applications or agents with tools, services, data sources, or enterprise systems.
• Experience with agent-to-agent (A2A) or multi-agent solution patterns, including communication or coordination among multiple agents.
• Hands-on experience developing retrieval-augmented generation (RAG) solutions, including retrieval, embeddings, vector search, and grounding LLM applications with enterprise data or content.
• Experience developing agentic workflows incorporating tool use, structured outputs, context management, orchestration, and human-in-the-loop patterns.
• Strong software development skills using modern programming languages, APIs, services, and application development frameworks.
• Experience integrating applications with APIs, databases, data sources, or enterprise systems.
• Understanding of modern software engineering practices, including source control, testing, debugging, code review, documentation, and maintainable code development.
• Strong client communication and interpersonal skills, including the ability to explain technical concepts to both technical and non-technical audiences.
• Ability to work effectively with clients and multidisciplinary teams in environments with evolving or ambiguous requirements.
• Demonstrated curiosity, innovative thinking, creative problem-solving, and ability to learn and apply new technologies quickly.
• Strong written and verbal communication skills.
• US Citizenship is contractually required.

• Bachelor’s degree from an accredited university.
• Prior experience working as a Forward Deployed Engineer, Forward Deployed Software Engineer, Forward Deployed AI Engineer, or in a similar client-embedded engineering role.
• Additional hands-on experience developing Claude-based solutions, including Claude Code, API development, tool use, Custom Skills, or Model Context Protocol.
• Anthropic Academy coursework or certificates in areas such as AI Fluency, API development, Model Context Protocol, Claude Code, or related platform topics.
• Anthropic partner training or certification experience, or equivalent platform-focused training.
• Experience building end-to-end agentic AI applications from prototype through implementation.
• Experience with testing and evaluation of generative AI or agentic AI systems, including validation, quality review, or regression testing.
• Experience with relational databases, data modeling, vector databases, or modern data platforms.
• Experience with cloud environments such as AWS, Microsoft Azure, or Google Cloud.
• Familiarity with AI safety, security, privacy, governance, and responsible AI practices.
• Experience with logging, monitoring, tracing, or observability for applications or AI-enabled systems.
• Experience delivering technology solutions in federal, regulated, or other complex enterprise environments.
• Experience delivering technology, data, AI, or digital solutions in healthcare, life sciences, public health, or other health-related environments.
• Familiarity with regulated health environments and considerations related to data privacy, security, governance, and responsible use of AI.
• Interest in continuing to develop expertise in forward deployed engineering, agentic AI, and client-facing technical delivery.

Compensation decisions depend on a wide range of factors, including but not limited to skill sets, experience and training, security clearances, licensure and certifications, and other business and organizational needs.