Lead / Principal Forward Deployed Engineer

Jaxel; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Jaxel is seeking a Lead/Principal Forward Deployed Engineer to embed with enterprise teams, shipping production AI agents and driving tool adoption. You will define standards, guardrails, and context strategies while collaborating with managers, product owners, and security teams to ensure robust, scalable AI-enabled software.

You will lead multi-step agent workflows, mentor engineers, and help raise AI fluency across engineering organizations.

Qualifications

• 7+ years in software engineering.
• 2+ years in customer-embedded/forward-deployed roles inside enterprise environments.
• Hands-on production experience building agents with Claude API/SDK and/or OpenAI Codex.
• Proven track record introducing AI development tools into engineering teams with measurable velocity impact.
• Experience structuring context for enterprise-scale repos: 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, and event-driven architectures.

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 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, rollback.
• Deploy agents that run in parallel with existing teams to accelerate delivery without disruption.
• Create evaluation harnesses 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, subdirectory conventions, skills, hooks, MCP integrations.
• Apply retrieval approaches per workload: JIT search, RAG/vector indexing for docs.
• Onboard teams to Claude Code, Cursor, Codex and related tools with guardrails.
• Coach teams on AI-assisted vs. agentic patterns.
• Run workshops and office hours to raise AI fluency.
• Leave durable artifacts like playbooks and templates for longevity.

Skills

Software engineering

Backend development

Full-stack development

Python

TypeScript/Node.js

Cloud & DevOps

Tools

Claude API

Claude Agent SDK

OpenAI Codex

Job description

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
• Remote work opportunity
• Professional growth and development
• Multicultural working environment