Lead Forward Deployed Engineer

New

BounteousEnterprise AI

Listing location: United States; Workplace type: Remote; Structured job location: United StatesFull-TimeLead

Salary not disclosed

Apply NowOpens the employer's application page

Job Details

Have 8+ years of experience in software engineering and solution architecture, including significant client-facing or forward-deployed delivery.
Have a track record of shipping LLM-based agents to production, ideally on Claude.
Bring hands-on experience with the Claude API, including tool use, structured outputs, prompt caching, and streaming.
Have experience with the Claude Agent SDK and MCP server development.
Use Claude Code and agentic coding practices fluently.
Have strong prompt and context engineering experience, including system prompts, tool descriptions, and skills for enterprise data.
Have experience designing evaluation frameworks and using them to guide engineering decisions.
Be proficient in Python and TypeScript, modern backend architecture, and cloud deployment; AWS is preferred.
Have enterprise data integration experience, including retrieval-augmented generation and agentic search over live systems.
Understand agent governance, security, observability, and risk controls.
Have experience leading teams in complex, regulated enterprise environments.
Preferred: Anthropic certification, regulated-industry experience, Claude Managed Agents or multiagent orchestration experience, and Claude deployments on AWS.

Own end-to-end technical design of agentic solutions on Claude, from discovery and workflow mapping through production rollout and continuous improvement.
Select agent patterns, runtimes, and deployment platforms based on workload, client cloud, and compliance needs.
Build and govern MCP servers, package domain expertise as Agent Skills, and apply context engineering for multi-step tasks.
Lead model strategy across Claude models and use caching, batch processing, and effort controls to manage cost.
Define human-in-the-loop checkpoints, permission scopes, and approval gates for each workflow's risk profile.
Lead and mentor engineers through the AI development lifecycle, using Claude Code and agentic coding practices.
Create evaluation suites from client tasks and gate releases on evaluation results.
Instrument observability and cost controls, including tracing agent sessions, tool calls, and token spend.
Embed with client teams, lead discovery and roadmap planning, and partner with risk, security, and governance stakeholders.
Support client rollout of Claude Enterprise, Claude Cowork, and Claude Code, and turn delivery learnings into reusable assets.

View Full Description & ApplyYou'll be redirected to the employer's site