Forward Deployed Engineer

Vivid Resourcing; United States; On-site; USD 180,000 - 240,000; Full time

Job summary

Vivid Resourcing seeks a Forward Deployed Engineer specializing in Claude and Generative AI to work directly with customers to design, build, and deploy production AI solutions. The role sits between software engineering, AI engineering, solution architecture, and consulting, translating business problems into technical applications using Claude APIs.

The position is remote with travel (10–25%). You should be a strong engineer who delivers working software, not just diagrams, and you will

Qualifications

• Experience building production AI applications with Claude/Anthropic APIs.
• Experience deploying LLM-powered applications into production environments.
• Strong software engineering background and ability to move from problems to working solutions.

Responsibilities

• Work with customers to identify high-value Claude/Generative AI use cases.
• Design and implement applications using Claude APIs and Anthropic ecosystem.
• Build production-grade AI applications, agents, workflows, and integrations.

Skills

Claude APIs

Anthropic APIs

LLM deployments

Prompt engineering

Agentic AI

Tool use / function calling

Python / TypeScript

System integration

Retrieval augmented generation

Observability

Tools

LangChain

LangGraph

AWS

Job description

We are looking for a Forward Deployed Engineer (FDE) specializing in Claude and Generative AI implementation to work directly with customers to design, build, and deploy production AI solutions.

This is a highly technical, customer-facing role sitting between software engineering, AI engineering, solution architecture, and consulting. You will take business problems from initial discovery through rapid prototyping and into production, using Anthropic Claude and modern agentic AI technologies.

The ideal candidate is a strong software engineer who is comfortable operating in ambiguous customer environments, translating business requirements into technical solutions, and building working applications rather than simply producing recommendations or architecture diagrams.

Key Responsibilities

• Work directly with customers to identify high-value use cases for Claude, Generative AI, and agentic AI.
• Design and implement applications using Claude APIs and Anthropic's ecosystem.
• Build production-grade AI applications, agents, workflows, and integrations.
• Develop solutions leveraging tool use/function calling, structured outputs, prompt engineering, RAG, and agentic workflows.
• Integrate Claude with existing enterprise applications, APIs, databases, SaaS platforms, and internal systems.
• Design and implement Model Context Protocol (MCP) integrations where appropriate.
• Rapidly prototype solutions and take successful proofs of concept through to production.
• Build backend services and APIs primarily using Python and/or TypeScript.
• Work with customer data and knowledge sources to develop retrieval and context-management architectures.
• Evaluate model outputs and improve accuracy, reliability, latency, and cost.
• Implement appropriate AI guardrails, security controls, observability, and evaluation frameworks.
• Run technical workshops, demonstrations, and discovery sessions with customers.
• Work closely with engineering and product teams to communicate recurring customer requirements and implementation challenges.
• Create reusable components, implementation patterns, and best practices that accelerate future deployments.

Required Experience

• Strong professional software engineering background.
• Hands-on experience building applications using Claude / Anthropic APIs.
• Experience deploying LLM-powered applications into production environments.
• Strong understanding of LLM concepts including:
• Prompt engineering and context management
• Tool/function calling
• AI agents and agentic workflows
• RAG and vector search
• Structured outputs
• LLM evaluation and observability
• Experience integrating AI applications with enterprise APIs, databases and third-party systems.
• Understanding of modern cloud infrastructure and application deployment.
• Ability to move quickly from an ambiguous business requirement to a working technical solution.
• Strong communication and stakeholder-management skills.
• Comfortable working directly with both technical and non-technical customer stakeholders.

Highly Desirable

Experience with any of the following would be particularly valuable:

• Anthropic SDKs
• AWS Bedrock / Claude on AWS
• Agent orchestration frameworks
• LangChain/LangGraph
• React / Next.js
• Enterprise authentication and authorization
• AI security and governance
• LLM evaluation frameworks
• Previous consulting, professional services, solutions engineering, or Forward Deployed Engineering experience

What We're Looking For

We are particularly interested in engineers who combine deep technical ability with strong customer instincts.

You should be comfortable entering a customer environment where the problem may initially be poorly defined, understanding what the customer is actually trying to achieve, building something quickly, gathering feedback, and iterating until the solution delivers measurable business value.

This isn't a pure research or advisory position. You will be expected to write code, build applications, integrate systems, solve problems, and deploy AI into real-world customer environments.

Ideal Background

The strongest candidates will have experience taking Claude or other frontier LLMs from proof-of-concept through to production, with demonstrable examples of AI applications they have personally designed and built.

This role is remote but will require some travel (10-25% per month).