Agentic Skill Engineer (skill.md & Workflows)
Standardize, author, and evaluate production-ready skill.md definitions, tool syntheses, execution sandboxes, and workflow automation plugins for autonomous coding agents.
Role Overview & Operational Scope
Skills are the functional executable units that transform raw models into capable engineers. You will author, validate, and optimize institutional `skill.md` definitions that package domain knowledge, tool schemas, scripts, and error recovery protocols into reusable, modular agent plugins.
Key Responsibilities & Production Deliverables
- Author robust, deterministic `skill.md` packages with structured YAML frontmatter, execution workflows, and reference scripts.
- Design standardized tool calling schemas and JSON contracts that eliminate agent parameter errors.
- Build isolated execution sandboxes (Docker/Wasm) for safe agent testing and script verification.
- Develop automated skill quality benchmarks assessing agent success rates across diverse real-world tasks.
- Curate Cehpoint's open and proprietary skill registry for enterprise client deployments.
Mandatory Foundational Knowledge
- Deep mastery of agent tool calling protocols, structured prompting, and zero-shot parameter extraction.
- Software packaging standards, semantic versioning, and plugin architecture principles.
- Linux command line, container isolation, and safe code execution sandbox design.
Mandatory Practical Skills & Architecture
- Strong multi-language programming proficiency in JavaScript/Node.js and Python.
- Expertise in writing crystal-clear, structured technical documentation, schemas, and markdown files.
- Experience building CI/CD test runners that evaluate agent execution trajectories.
Problem Solving, Execution Rigor & Curiosity
- Builder mindset obsessed with modularity, composability, and developer experience.
- Extreme attention to detail in documentation syntax, schema validation, and edge-case handling.
- Active participant in open-source agent ecosystems and tooling discussions.
5-Day Live Technical Evaluation Milestone
5-Day Live Practical Milestone: Build and validate 5 enterprise-grade skill.md packages with deterministic verification scripts, tool mocks, and error boundaries for real-world developer workflows (strictly 5 working days).
Institutional Hiring Protocol: Candidates who pass initial resume screening are invited to a live, practical evaluation milestone spanning strictly not more than 5 working days. Verifiable completion and code audit by your assigned senior engineering mentor is the sole prerequisite for official corporate offer letter issuance.
Compensation, Total Rewards & Advancement
- Competitive salary (₹10,00,000–₹18,00,000) with project incentive bonuses.
- Ownership of Cehpoint's flagship agent skill ecosystem and public open-source releases.
- 100% remote flexibility with home office setup reimbursement.
- Fast-track advancement into Agent Platform Lead.
Dedicated Inquiries Inbox for This Role
Have questions regarding architecture scope or wish to share private research repos directly? Messages sent to this address route straight to the engineering leads reviewing this opening.
agentic-skill-engineer-careers@cehpoint.co.in
Open Mail Client →