Lead / Principal Forward Deployed Engineer

About This Role
We're building a forward-deployed engineering practice at the frontier of AI-native software development — and we're looking for someone who wants to be on the ground floor of that.
This is not a consulting role where you deliver recommendations from the outside. You'll embed as a technical insider within enterprise engineering organizations, work alongside their teams daily, and be directly responsible for shipping production AI agents, driving tool adoption, and raising the AI fluency of every engineer you work with.

Responsibilities
Join the client's daily engineering rituals: standups, code reviews, sprint planning, and incident response
Serve as the primary technical authority for AI-assisted and agentic development within assigned squads
Define coding standards, prompt engineering playbooks, and guardrails teams can follow independently
Bridge engineering managers, product owners, and security stakeholders with hands-on implementation
Design and ship autonomous agents using Claude API, Claude Code, OpenAI Codex, or equivalent platforms
Build multi-step agent workflows: task decomposition, tool calling, subagent orchestration, error handling, and rollback
Deploy agents that run in parallel with existing teams — accelerating delivery without disrupting live workflows
Create evaluation harnesses (golden datasets, regression suites, LLM-as-judge) to ensure agent reliability in production
Structure API documentation, architecture patterns, and domain knowledge into machine-readable context for AI tools
Implement layered context strategies: rules files (CLAUDE.md / AGENTS.md), subdirectory conventions, skills, hooks, and MCP integrations
Apply the right retrieval approach per workload: agentic just-in-time search for live code; RAG/vector indexing for stable documentation
Onboard engineering teams to Claude Code, Cursor, Codex, and related tools with team-specific guardrails
Coach teams on AI-assisted vs. agentic development patterns
Run workshops, pair programming sessions, and office hours to raise organization-wide AI fluency
Leave durable artifacts — playbooks, templates, eval suites, context files — that outlast the engagement
Conduct technical discovery to map business problems to agentic solutions
Ship a working prototype in the first week; iterate toward production deployment
Own agent harness architecture: session management, concurrency, approval boundaries, audit trails
Mentor client engineers and junior FDEs adopting AI-native workflows
Requirements
7+ years in software engineering
2+ years in customer-embedded, forward-deployed, or technical anchor roles inside enterprise engineering organizations
Hands-on production experience building agents with Claude API, Claude Agent SDK, and/or OpenAI Codex
Proven track record introducing AI development tools (Claude Code, Cursor, or similar) into engineering teams with measurable velocity impact
Experience structuring context for enterprise-scale repositories: API contracts, architecture docs, layered rules files
Strong backend or full-stack skills in Python, TypeScript/Node.js, Java, or Go
Experience with microservices, REST/GraphQL APIs, and event-driven architectures (Kafka or equivalent)
Cloud deployment experience on AWS, GCP, or Azure; CI/CD, Docker, and modern DevOps practices
Based in the San Francisco Bay Area; authorized to work in the US; available for onsite or hybrid work (3–5 days/week)
Nice to Have
Experience with MCP server design and custom agent tool development
Production experience with RAG pipelines, vector databases, and LLM orchestration frameworks
Built evaluation frameworks for LLM/agent systems: golden datasets, regression testing, safety guardrails
Experience with AI security patterns: subagent permission scoping, automated auditing, data residency constraints
Familiarity with large-scale e-commerce platforms, multi-tenant architectures, or omnichannel retail systems
Anthropic certification: Claude Certified Architect, Foundations (CCA-F) or equivalent Anthropic Academy credentials
AWS or GCP professional certifications
Experience with Vue.js / React or Java/Spring Boot in large production codebases
Open-source contributions to agent tooling or the MCP ecosystem
Benefits
Competitive salary
Remote work opportunity
Comfortable work in your local time zone
Flexible work schedule
Professional growth and development
Multicultural working environment