Forward Deployed Engineer, Agentic AI

Forward Deployed Engineer, Agentic AI

About the Role

Redapt is building dedicated capacity to design, deploy, and optimize agentic AI solutions for clients. We are looking for a Forward Deployed Engineer: a technical, client-facing builder who can turn AI capabilities into working production systems inside customer environments.

This role blends an embedded, hands-on delivery model with the broader technical advisory work Redapt clients need to get real ROI from AI investments. You will write production Python code, sit in front of clients to explain technical tradeoffs in plain language, and help both customers and internal Redapt teams get more value out of their existing AI workloads.

This role is intentionally broader than a typical FDE position, combining embedded delivery with elements of technical advisory work, such as token and model optimization, AI security, and workload ROI, that support long-term client success.

What You'll Do

• Embedded Delivery & Engineering
• Embed directly with client teams to design, build, and ship production applications and integrations built on Claude models.
• Architect multi-agent systems with reliable tool use, memory, and orchestration patterns that perform accurately in high-stakes environments
• Write and maintain production-quality Python code for AI integrations, agent workflows, and internal tooling.
• Set up and configure agentic harnesses (including Azure Foundry, AWS Bedrock, Claude Cowork-style deployments) so client teams can put AI to work on real business processes
• Instrument and monitor agentic systems in production using observability tooling; iterate rapidly based on real user behavior and feedback
• Client Advisory & Stakeholder Engagement
• Present findings, architecture options, and recommendations directly to client stakeholders, translating technical concepts for both technical and non-technical audiences
• Build durable, trusted relationships with client technical and business stakeholders over the life of an engagement.
• Partner with product managers and customer success to deeply understand user problems and translate them into elegant, production-grade AI solutions
• Work with internal teams to assess existing AI workloads and identify opportunities to improve ROI, whether through better architecture, tooling, or workflow redesign.
• Model Optimization & AI Security
• Advise clients and internal Redapt teams on token optimization and model selection to control cost and improve performance.
• Evaluate and tune model configuration and prompting strategy to improve output quality and reliability for a given workload.
• Identify AI security considerations (data handling, access control, prompt injection, model governance) and build these into deployment recommendations
• Collaborate cross-functionally with engineers, data teams, and compliance stakeholders to ensure AI outputs meet accuracy and regulatory standards
• Required Qualifications
• 3+ years in a technical, client-facing role such as forward deployed engineering, solutions engineering, or consulting with a software engineering background
• At least 1 year building and shipping AI/LLM-powered applications in production
• Strong coding skills in Python and TypeScript; comfort working across the stack as needed
• Strong understanding of agentic patterns: tool use, RAG, memory management, multi-agent orchestration, and human-in-the-loop design
• Demonstrated ability to communicate clearly and credibly with clients, including in live, in-person settings
• Working knowledge of Azure Foundry, AWS Bedrock, OpenAI/Codex and the Anthropic/Claude platform (Claude API, tool use, Claude Code, or similar)
• Comfort operating with ambiguity and owning a technical engagement end-to-end.

Preferred Qualifications

• Experience with evaluation frameworks, RAG pipelines, or agent orchestration frameworks (e.g., LangGraph, LangChain, CrewAI).
• Familiarity with AI security, privacy, and governance considerations in enterprise environments.
• Experience with MLOps/LLMOps practices, including model monitoring and prompt management.
• Prior experience specifically with Azure Foundry, AWS Bedrock, or Anthropic's Claude platform (Claude for Enterprise, Claude Code, MCP).
• Background in enterprise IT systems or AI deployment patterns.

What Makes You Successful

You can translate deep technical work into plain language that lands with engineers and executives alike.

You thrive working embedded inside client environments and take ownership of outcomes, not just recommendations.

You are comfortable operating across the full arc of an engagement, from writing production code to advising on cost, security, and architecture.

You enjoy turning one-off engagement learnings into repeatable patterns so the next client moves faster.

Technologies & Methodologies

Python

OpenAI / Codex

• Anthropic / Claude API
• Agentic AI & Agent Development
• Azure AI Foundry

AWS Bedrock

• AI Security & Governance
• RAG Pipelines (Preferred)
• LangGraph / LangChain / CrewAI (Preferred)
• MLOps / LLMOps (Preferred)
• MCP (Model Context Protocol) (Preferred)

Travel required:

Travel typically 20% or less a year

Equal Employment Opportunity: