Lead Forward Deployed Engineer (FDE)

Bounteous

1d•Remote

About The Position

Bounteous is a global AI Services firm with more than 5,000 team members worldwide. It helps organizations design, build, and scale AI-driven products, platforms, and processes, and is backed by New Mountain Capital. The Lead Forward Deployed Engineer (FDE) is the senior technical anchor for Bounteous client engagements built on Claude. The role embeds with client teams to identify workflows where agents can change business outcomes and deliver governed, production-grade agentic systems on Anthropic's stack. It combines hands-on engineering, solution architecture, and client leadership. The FDE leads integrated squads using Bounteous Arc, a framework for a hardened, repeatable, governable agentic development lifecycle with Claude Code, and turns field learnings into reusable patterns for future engagements. The role owns technical design from discovery through production rollout and continuous improvement; selects suitable agent patterns, runtimes, models, and deployment platforms; designs governed tools and context; and establishes evaluation, observability, cost, and risk controls. It also mentors distributed engineering teams, partners with client and Anthropic stakeholders, and supports lasting client adoption of Claude products and capabilities. The position includes information security responsibilities: promoting security practices, identifying and reporting risks to information assets, evaluating data handling for privacy and protection compliance, and integrating data protection throughout the information lifecycle. Bounteous is an equal opportunity employer and is willing to sponsor eligible candidates for employment visas.

Requirements

8+ years of experience in software engineering and solution architecture, including significant client-facing or forward-deployed delivery.
Track record of shipping LLM-based agents to production, ideally on Claude.
Hands-on experience with the Claude API, including tool use, structured outputs, prompt caching, and streaming; the Claude Agent SDK; and MCP server development.
Daily fluency with Claude Code and agentic coding practices.
Strong prompt and context engineering skills, including system prompts, tool descriptions, and skills that work with messy enterprise data.
Experience designing evaluation frameworks and using them to guide engineering decisions.
Proficiency in Python and TypeScript, modern backend architecture, and cloud deployment.
Enterprise data integration experience, including selecting between retrieval-augmented generation and agentic search over live systems.
Strong understanding of agent governance, security, observability, and risk controls.
Experience leading teams in complex, regulated enterprise environments.

Nice To Haves

Anthropic certification, such as Claude Certified Architect (Foundations or Professional).
Prior experience in BFSI or other regulated industries.
Production experience with Claude Managed Agents or multiagent orchestration.
Claude deployments on AWS, including IAM, network isolation, and data residency requirements.
Experience rolling out Claude Enterprise or Claude Cowork with admin-managed skills and plugins.
Experience in global, distributed delivery models.
Contributions to the MCP or Agent Skills ecosystems, or other open-source work.

Responsibilities

Own end-to-end technical design of Claude-based agentic solutions, from discovery and workflow mapping through production rollout and continuous improvement.
Select agent design patterns and runtimes appropriate to each use case, client cloud, and compliance needs.
Design and govern MCP servers, Agent Skills, and context-engineering approaches for accurate agent performance across long tasks.
Lead model strategy across the Claude family and use cost-management capabilities to keep costs predictable.
Define human-in-the-loop checkpoints, permission scopes, and approval gates based on workflow risk.
Lead and mentor engineers across geographies and disciplines through an AI development lifecycle.
Use Claude Code and agentic coding practices, including subagents, hooks, plugins, project memory conventions, and headless CI runs.
Define success criteria and evaluation suites using real client tasks, and gate releases on evaluation results.
Instrument observability and cost controls, including tracing agent sessions, tool calls, and token spend.
Ship production artifacts and harden reusable assets for use across engagements.
Embed with client engineering, platform, and business teams as their primary technical point of contact, including on-site when needed.
Run discovery to identify measurable agent value and translate findings into phased, fundable roadmaps.
Partner with client risk, security, and governance stakeholders on data handling, MCP approval, audit logging, and enterprise admin controls.
Collaborate with Anthropic account and Applied AI teams on joint engagements.
Help client teams adopt Claude Enterprise, Claude Cowork, and Claude Code with organization-managed skills and plugins.
Promote and enforce information security practices, including acceptable use, malware protection, and password security.
Identify, assess, and report security risks affecting information asset confidentiality, integrity, and availability.
Evaluate how data is stored, processed, and transmitted to support compliance with privacy and protection standards such as GDPR and CCPA.
Integrate data protection measures throughout the information lifecycle.