@sparring/tech-roles-library
Version:
Comprehensive tech roles and competencies library for 78 technical roles with 9 career levels each. Includes detailed competencies and career progression paths with complete bilingual support (EN/ES).
260 lines (259 loc) • 9.32 kB
JSON
{
"role": "Site Reliability Engineer",
"category": "Software Engineering",
"levels": {
"SRE-L1": {
"level": "L1 - SRE Trainee",
"levelNumber": 1,
"yearsRange": {
"min": 0,
"max": 1
},
"coreCompetencies": [
"Basic understanding of SRE principles and SLI/SLO/SLA",
"Elementary knowledge of monitoring and observability",
"Ability to respond to incidents with runbooks",
"Basic understanding of availability and reliability",
"Ability to use basic monitoring tools",
"Elementary knowledge of incident management",
"Basic understanding of automation and scripting",
"Ability to document operational procedures"
],
"complementaryCompetencies": [
"Basic knowledge of cloud platforms",
"Familiarity with containerization",
"Elementary understanding of networking"
],
"indicators": [
"Requires constant supervision in SRE tasks",
"Participates in on-call with senior support",
"Needs 6-12 months of SRE mentoring"
]
},
"SRE-L2": {
"level": "L2 - SRE Junior I",
"levelNumber": 2,
"yearsRange": {
"min": 1,
"max": 2
},
"coreCompetencies": [
"Ability to define and monitor basic SLIs",
"Ability to implement effective alerting",
"Practical knowledge of basic capacity planning",
"Understanding of error budgets and their management",
"Ability to perform basic post-mortems",
"Ability to automate simple operational tasks",
"Knowledge of load balancing and failover",
"Understanding of backup and recovery procedures"
],
"complementaryCompetencies": [
"Knowledge of Infrastructure as Code",
"Ability for basic performance tuning",
"Understanding of security operations"
],
"indicators": [
"Handles medium severity incidents independently",
"Improves runbooks and documentation proactively",
"Participates effectively in on-call rotation"
]
},
"SRE-L3": {
"level": "L3 - SRE Junior II",
"levelNumber": 3,
"yearsRange": {
"min": 2,
"max": 3
},
"coreCompetencies": [
"Mastery of complete observability (metrics, logs, traces)",
"Ability to design comprehensive SLOs",
"Ability to implement basic chaos engineering",
"Deep knowledge of distributed systems reliability",
"Ability to perform advanced capacity planning",
"Solid understanding of toil reduction and automation",
"Ability to implement self-healing systems",
"Knowledge of disaster recovery planning"
],
"complementaryCompetencies": [
"Knowledge of service mesh",
"Ability for cost optimization",
"Understanding of compliance automation"
],
"indicators": [
"Leads response to complex incidents",
"Designs monitoring systems for new services",
"Reduces toil significantly through automation"
]
},
"SRE-L4": {
"level": "L4 - SRE Mid-Level I",
"levelNumber": 4,
"yearsRange": {
"min": 3,
"max": 5
},
"coreCompetencies": [
"Ability to design architectures for high availability",
"Mastery of incident command and crisis management",
"Ability to implement SRE practices at scale",
"Deep knowledge of performance engineering",
"Ability to define organizational reliability standards",
"Mastery of blameless post-mortem culture",
"Ability to design disaster recovery strategies",
"Knowledge of multi-region failover and geo-redundancy"
],
"complementaryCompetencies": [
"Knowledge of machine learning for SRE",
"Ability for game days and drills",
"Understanding of edge reliability"
],
"indicators": [
"Defines SRE strategy for critical products",
"Mentors junior SREs effectively",
"Improves MTTR and MTBF consistently"
]
},
"SRE-L5": {
"level": "L5 - SRE Mid-Level II",
"levelNumber": 5,
"yearsRange": {
"min": 5,
"max": 7
},
"coreCompetencies": [
"Expertise in reliability engineering for massive systems",
"Ability to implement AIOps and predictive analytics",
"Mastery of global load balancing and traffic management",
"Ability to design observability platforms",
"Deep knowledge of advanced chaos engineering",
"Ability to lead SRE transformations",
"Expertise in production readiness reviews",
"Mastery of reliability testing and validation"
],
"complementaryCompetencies": [
"Knowledge of quantum-safe reliability",
"Ability for reliability economics",
"Understanding of sustainability in SRE"
],
"indicators": [
"Architects reliability for multiple products",
"Leads cross-organizational SRE initiatives",
"Defines technical reliability roadmap"
]
},
"SRE-L6": {
"level": "L6 - SRE Senior I",
"levelNumber": 6,
"yearsRange": {
"min": 7,
"max": 10
},
"coreCompetencies": [
"Ability to define enterprise SRE strategy",
"Expertise in reliability for complex architectures",
"Mastery of incident management at global scale",
"Ability to build SRE platforms and tooling",
"Deep knowledge of reliability economics and ROI",
"Ability to lead cultural transformation towards SRE",
"Expertise in vendor reliability management",
"Mastery of regulatory compliance for availability"
],
"complementaryCompetencies": [
"Knowledge of reliability for AI/ML systems",
"Ability for reliability consulting",
"Understanding of reliability insurance"
],
"indicators": [
"Defines corporate reliability standards",
"Leads SRE organization building",
"Influences industry SRE practices"
]
},
"SRE-L7": {
"level": "L7 - SRE Senior II",
"levelNumber": 7,
"yearsRange": {
"min": 10,
"max": 12
},
"coreCompetencies": [
"Leadership in reliability engineering innovation",
"Ability to design reliability for ecosystems",
"Expertise in zero-downtime transformation",
"Mastery of reliability automation platforms",
"Ability to define SRE methodologies",
"Deep knowledge of reliability impact on revenue",
"Expertise in building SRE centers of excellence",
"Ability to lead reliability research"
],
"complementaryCompetencies": [
"Ability to patent reliability innovations",
"Ability for global SRE evangelism",
"Knowledge of reliability ventures"
],
"indicators": [
"Defines organizational SRE philosophy",
"Keynote speaker at SREcon",
"Author of SRE frameworks"
]
},
"SRE-L8": {
"level": "L8 - SRE Principal/Staff",
"levelNumber": 8,
"yearsRange": {
"min": 12,
"max": 15
},
"coreCompetencies": [
"Strategic vision for the future of reliability engineering",
"Ability to transform industries through reliability",
"Expertise in reliability for critical infrastructure",
"Mastery of executive reliability governance",
"Ability to define reliability economics models",
"Deep knowledge of global reliability standards",
"Expertise in strategic reliability partnerships",
"Ability to lead open source SRE initiatives"
],
"complementaryCompetencies": [
"Ability to influence reliability regulations",
"Ability for reliability advisory boards",
"Knowledge of reliability investments"
],
"indicators": [
"Defines multi-year reliability strategy",
"Influences global reliability standards",
"Advisor to C-suite on reliability"
]
},
"SRE-L9": {
"level": "L9 - VP SRE/Head of Reliability",
"levelNumber": 9,
"yearsRange": {
"min": 15,
"max": null
},
"coreCompetencies": [
"Executive leadership in reliability and operations",
"Ability to convert reliability into competitive advantage",
"Expertise in enterprise reliability transformation",
"Mastery of strategic reliability budgets",
"Ability to build global SRE organizations",
"Deep knowledge of reliability risk management",
"Expertise in reliability as market differentiator",
"Ability to define reliability culture",
"Mastery of reliability metrics for boards"
],
"complementaryCompetencies": [
"Ability to create reliability companies",
"Ability for reliability M&A",
"Knowledge of reliability IPOs"
],
"indicators": [
"Defines and executes enterprise reliability vision",
"Responsible for all corporate reliability",
"Recognized global leader in reliability engineering"
]
}
}
}