Pipeline run
ef02699b-236f-448e-b3d7-0f1be5b3dbdd
Pipeline LLM cost (USD)
API 1: $0.0037
API 2: $0.0000
API 3: $0.0000
Total: $0.0037
Client output enrichment
v2 Skill cluster · Nature of work · AI index · Tech stack maturity · Evidence · KRA descriptionNature of work
—
Tech stack maturity
Mainstream Modern
AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)
0.00 / 5
· Title match
· Has AI skill
· AI skill (primary)
· AI skill (secondary)
· On AI team
· Builds AI products
vocab breakdown (legacy)
Assistants (×1):
—
Frameworks (×2):
—
Models / concepts (×3):
—
Evidence — skills matched in JD (23)
COBOL
IBM z/OS
JCL
CICS
BMS
SQL
DB2
VSAM
KSDS
ESDS
RRDS
IDCAMS
SDSF
Abend-AID
IBM Fault Analyzer
Endevor
ChangeMan ZMF
Strobe
APA
MQ Series
IBM Connect:Direct
Java
Python
Skill cluster (0 dimension groups, role-scoped)
Show KRA description ↓
- Develop and maintain COBOL batch programs running on IBM z/OS, using JCL job streams and proc libraries
- Build CICS online programs with BMS maps for terminal-based banking transactions and customer service screens
- Write embedded SQL in COBOL programs against DB2 z/OS tables, optimize plan binding and BIND options
- Maintain VSAM file structures (KSDS, ESDS, RRDS) and perform reorganizations with IDCAMS utilities
- Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis
- Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments
- Tune COBOL programs for CPU and elapsed-time efficiency using Strobe or APA performance analyzers
- Integrate mainframe batch output with downstream Java and Python systems via MQ Series and IBM Connect:Direct
Signals
Skill
data-engineer
0.05
Alias
mainframe-developer
1.00
KRA
backend-engineer
0.43
Post-classification
Centroid—
Alias collision log—
New-role queue#50
New skills captured0
New KRA captured—
Status:
extract_from_jd_done
Created: 2026-05-21T17:50:48.567100Z
Updated: 2026-05-21T17:50:49.089126Z
Flow
Current 3-step pipeline
1 POST /skills/extract-from-jd
2 POST /skills/extract-details
3 POST /skills/final-role-output
Role
Chosen role & resolution
No chosen role stored for this run.
Job description
Job Title: Mainframe COBOL Developer Company: LegacyBank Systems Location: Chennai, India Experience: 7+ years About the Role: We are hiring a Mainframe COBOL Developer to maintain and modernize our IBM z/OS core banking platform. You will work on batch processing systems handling 50M daily transactions, CICS online programs, and DB2 z/OS database integration. Key Responsibilities: - Develop and maintain COBOL batch programs running on IBM z/OS, using JCL job streams and proc libraries - Build CICS online programs with BMS maps for terminal-based banking transactions and customer service screens - Write embedded SQL in COBOL programs against DB2 z/OS tables, optimize plan binding and BIND options - Maintain VSAM file structures (KSDS, ESDS, RRDS) and perform reorganizations with IDCAMS utilities - Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis - Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments - Tune COBOL programs for CPU and elapsed-time efficiency using Strobe or APA performance analyzers - Integrate mainframe batch output with downstream Java and Python systems via MQ Series and IBM Connect:Direct Required Qualifications: - 7+ years COBOL programming on IBM z/OS - Expert in JCL, CICS, DB2 z/OS, VSAM file handling - Experience with Endevor, ChangeMan ZMF, MQ Series - Hands-on with SDSF, IBM Debug Tool, Abend-AID
Skills from this JD
Each row merges API 1 extraction, API 2 library match / v3 orchestration (dimensions + locked dims), and API 3 persistence tags.
COBOL
Primary
No API 2 row (run stopped after API 1 or history missing)
IBM z/OS
Primary
No API 2 row (run stopped after API 1 or history missing)
JCL
Primary
No API 2 row (run stopped after API 1 or history missing)
CICS
Primary
No API 2 row (run stopped after API 1 or history missing)
BMS
Primary
No API 2 row (run stopped after API 1 or history missing)
SQL
Primary
No API 2 row (run stopped after API 1 or history missing)
DB2
Primary
No API 2 row (run stopped after API 1 or history missing)
VSAM
Primary
No API 2 row (run stopped after API 1 or history missing)
KSDS
Primary
No API 2 row (run stopped after API 1 or history missing)
ESDS
Primary
No API 2 row (run stopped after API 1 or history missing)
RRDS
Primary
No API 2 row (run stopped after API 1 or history missing)
IDCAMS
Primary
No API 2 row (run stopped after API 1 or history missing)
SDSF
Primary
No API 2 row (run stopped after API 1 or history missing)
Abend-AID
Primary
No API 2 row (run stopped after API 1 or history missing)
IBM Fault Analyzer
Primary
No API 2 row (run stopped after API 1 or history missing)
Endevor
Primary
No API 2 row (run stopped after API 1 or history missing)
ChangeMan ZMF
Primary
No API 2 row (run stopped after API 1 or history missing)
Strobe
Primary
No API 2 row (run stopped after API 1 or history missing)
APA
Primary
No API 2 row (run stopped after API 1 or history missing)
Java
Secondary
No API 2 row (run stopped after API 1 or history missing)
Python
Secondary
No API 2 row (run stopped after API 1 or history missing)
MQ Series
Primary
No API 2 row (run stopped after API 1 or history missing)
IBM Connect:Direct
Primary
No API 2 row (run stopped after API 1 or history missing)
Library artifacts (this run)
No artifact rows for this run.
nano JD Parser — gpt-4.1-nano click to toggle
RoleMainframe COBOL Developer
CompanyLegacyBank Systems
Experience7+ years
DomainBanking
Location
Chennai, India
JD type
pass
Show raw JSON
{
"JD_type": "pass",
"about_company": null,
"certifications": [],
"company_name": "LegacyBank Systems",
"ctc": null,
"domain": {
"primary": {
"aliases": [
"BFSI",
"Retail Banking"
],
"domain": "Banking"
},
"secondary": null
},
"education": [],
"experience": {
"max": null,
"min": 7,
"raw": "7+ years"
},
"job_locations": [
{
"aliases": [
"Madras"
],
"city": "Chennai",
"country": "India",
"state": null,
"work_mode": null
}
],
"role": "Mainframe COBOL Developer",
"role_aliases": [
"COBOL Developer",
"Mainframe Developer"
],
"role_archetype": "Engineering",
"roles_and_responsibilities": [
{
"bullet_count": 8,
"heading": "Key Responsibilities",
"heading_was_present": true,
"source_marker": {
"first_5_words": "Develop and maintain COBOL batch",
"last_5_words": "Java and Python systems via MQ"
},
"text": "- Develop and maintain COBOL batch programs running on IBM z/OS, using JCL job streams and proc libraries\n- Build CICS online programs with BMS maps for terminal-based banking transactions and customer service screens\n- Write embedded SQL in COBOL programs against DB2 z/OS tables, optimize plan binding and BIND options\n- Maintain VSAM file structures (KSDS, ESDS, RRDS) and perform reorganizations with IDCAMS utilities\n- Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis\n- Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments\n- Tune COBOL programs for CPU and elapsed-time efficiency using Strobe or APA performance analyzers\n- Integrate mainframe batch output with downstream Java and Python systems via MQ Series and IBM Connect:Direct",
"word_count": 134
}
],
"urls": []
}
API 1 — extract-from-jd click to toggle
{
"final_skills": [
{
"is_primary": true,
"skill_name": "COBOL"
},
{
"is_primary": true,
"skill_name": "IBM z/OS"
},
{
"is_primary": true,
"skill_name": "JCL"
},
{
"is_primary": true,
"skill_name": "CICS"
},
{
"is_primary": true,
"skill_name": "BMS"
},
{
"is_primary": true,
"skill_name": "SQL"
},
{
"is_primary": true,
"skill_name": "DB2"
},
{
"is_primary": true,
"skill_name": "VSAM"
},
{
"is_primary": true,
"skill_name": "KSDS"
},
{
"is_primary": true,
"skill_name": "ESDS"
},
{
"is_primary": true,
"skill_name": "RRDS"
},
{
"is_primary": true,
"skill_name": "IDCAMS"
},
{
"is_primary": true,
"skill_name": "SDSF"
},
{
"is_primary": true,
"skill_name": "Abend-AID"
},
{
"is_primary": true,
"skill_name": "IBM Fault Analyzer"
},
{
"is_primary": true,
"skill_name": "Endevor"
},
{
"is_primary": true,
"skill_name": "ChangeMan ZMF"
},
{
"is_primary": true,
"skill_name": "Strobe"
},
{
"is_primary": true,
"skill_name": "APA"
},
{
"is_primary": false,
"skill_name": "Java"
},
{
"is_primary": false,
"skill_name": "Python"
},
{
"is_primary": true,
"skill_name": "MQ Series"
},
{
"is_primary": true,
"skill_name": "IBM Connect:Direct"
}
],
"jd_role": {
"display_name": "Mainframe COBOL Developer",
"rationale": null,
"role_aliases": [
"COBOL Developer",
"Mainframe Developer"
],
"role_archetype": "Engineering",
"slug": ""
},
"nano_parsed": {
"JD_type": "pass",
"about_company": null,
"certifications": [],
"company_name": "LegacyBank Systems",
"ctc": null,
"domain": {
"primary": {
"aliases": [
"BFSI",
"Retail Banking"
],
"domain": "Banking"
},
"secondary": null
},
"education": [],
"experience": {
"max": null,
"min": 7,
"raw": "7+ years"
},
"job_locations": [
{
"aliases": [
"Madras"
],
"city": "Chennai",
"country": "India",
"state": null,
"work_mode": null
}
],
"role": "Mainframe COBOL Developer",
"role_aliases": [
"COBOL Developer",
"Mainframe Developer"
],
"role_archetype": "Engineering",
"roles_and_responsibilities": [
{
"bullet_count": 8,
"heading": "Key Responsibilities",
"heading_was_present": true,
"source_marker": {
"first_5_words": "Develop and maintain COBOL batch",
"last_5_words": "Java and Python systems via MQ"
},
"text": "- Develop and maintain COBOL batch programs running on IBM z/OS, using JCL job streams and proc libraries\n- Build CICS online programs with BMS maps for terminal-based banking transactions and customer service screens\n- Write embedded SQL in COBOL programs against DB2 z/OS tables, optimize plan binding and BIND options\n- Maintain VSAM file structures (KSDS, ESDS, RRDS) and perform reorganizations with IDCAMS utilities\n- Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis\n- Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments\n- Tune COBOL programs for CPU and elapsed-time efficiency using Strobe or APA performance analyzers\n- Integrate mainframe batch output with downstream Java and Python systems via MQ Series and IBM Connect:Direct",
"word_count": 134
}
],
"urls": []
},
"rejected": false,
"rejection_reason": null,
"run_id": "ef02699b-236f-448e-b3d7-0f1be5b3dbdd",
"stage3_signals": {
"alias_found": true,
"alias_match_roles": [
{
"display_name": "Mainframe Developer",
"kra_matches": null,
"matched_count": null,
"matched_skills": null,
"role_id": 30,
"score": 1.0,
"slug": "mainframe-developer",
"total_count": null
}
],
"kra_match_roles": [
{
"display_name": "Backend Developer",
"kra_matches": [
{
"kra_text": "Integrates with third-party services, payment gateways, messaging queues like Kafka or RabbitMQ, and internal microservices via HTTP and event-driven patterns.",
"sentence": "Integrate mainframe batch output with downstream Java and Python systems via MQ Series and IBM Connect:Direct",
"similarity": 0.4842
},
{
"kra_text": "Investigates and resolves production incidents, API bugs, and service degradation through root cause analysis, hotfixes, and post-mortems.",
"sentence": "Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis",
"similarity": 0.4123
},
{
"kra_text": "Writes database access logic including SQL queries, ORM mappings, stored procedures, and migration scripts for relational databases like PostgreSQL and MySQL.",
"sentence": "Write embedded SQL in COBOL programs against DB2 z/OS tables, optimize plan binding and BIND options",
"similarity": 0.4047
}
],
"matched_count": null,
"matched_skills": null,
"role_id": 1,
"score": 0.4337,
"slug": "backend-engineer",
"total_count": null
},
{
"display_name": "Data Engineer",
"kra_matches": [
{
"kra_text": "Develops batch and real-time streaming data pipelines using Apache Spark, Apache Kafka, Apache Flink, or Airflow for data movement and processing at scale.",
"sentence": "Integrate mainframe batch output with downstream Java and Python systems via MQ Series and IBM Connect:Direct",
"similarity": 0.445
},
{
"kra_text": "Designs dimensional models, star schemas, data vault structures, and curated data mart tables to support BI tools and self-service analytics consumption.",
"sentence": "Maintain VSAM file structures (KSDS, ESDS, RRDS) and perform reorganizations with IDCAMS utilities",
"similarity": 0.4327
},
{
"kra_text": "Monitors pipeline health, SLA breach alerts, and job failure notifications, and performs root cause analysis for data pipeline incidents.",
"sentence": "Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis",
"similarity": 0.3877
}
],
"matched_count": null,
"matched_skills": null,
"role_id": 2,
"score": 0.4218,
"slug": "data-engineer",
"total_count": null
},
{
"display_name": "Fullstack Developer",
"kra_matches": [
{
"kra_text": "Debugs full-stack issues that span frontend rendering, API behavior, database queries, and infrastructure configuration to identify root causes.",
"sentence": "Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis",
"similarity": 0.4179
},
{
"kra_text": "Delivers features through CI/CD pipelines using automated tests, staged rollouts, feature flags, and incremental deployments.",
"sentence": "Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments",
"similarity": 0.4063
},
{
"kra_text": "Designs and queries relational databases like PostgreSQL and document stores like MongoDB, writing migrations, indexes, and optimized queries.",
"sentence": "Write embedded SQL in COBOL programs against DB2 z/OS tables, optimize plan binding and BIND options",
"similarity": 0.3993
}
],
"matched_count": null,
"matched_skills": null,
"role_id": 15,
"score": 0.4078,
"slug": "full-stack-engineer",
"total_count": null
},
{
"display_name": "ML Ops Engineer",
"kra_matches": [
{
"kra_text": "Coordinates model promotion workflows across development, staging, and production environments including integration testing and data contract validation.",
"sentence": "Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments",
"similarity": 0.4938
},
{
"kra_text": "Maintains ML platform runbooks, on-call escalation playbooks, and deployment procedure documentation for production operations teams.",
"sentence": "Develop and maintain COBOL batch programs running on IBM z/OS, using JCL job streams and proc libraries",
"similarity": 0.3611
},
{
"kra_text": "Maintains ML platform runbooks, on-call escalation playbooks, and deployment procedure documentation for production operations teams.",
"sentence": "Maintain VSAM file structures (KSDS, ESDS, RRDS) and perform reorganizations with IDCAMS utilities",
"similarity": 0.3451
}
],
"matched_count": null,
"matched_skills": null,
"role_id": 16,
"score": 0.4,
"slug": "ml-ops-engineer",
"total_count": null
},
{
"display_name": "DevOps Engineer",
"kra_matches": [
{
"kra_text": "Sets up and maintains development, staging, and production environments with consistent configuration management using Ansible, Puppet, or Chef.",
"sentence": "Use Endevor or ChangeMan ZMF for source code management and promotion through dev/test/prod environments",
"similarity": 0.4869
},
{
"kra_text": "Collaborates with development teams to improve build processes, reduce deployment friction, containerize applications, and adopt DevOps best practices.",
"sentence": "Develop and maintain COBOL batch programs running on IBM z/OS, using JCL job streams and proc libraries",
"similarity": 0.3593
},
{
"kra_text": "Responds to deployment failures, infrastructure incidents, and environment misconfiguration issues to restore service availability and prevent recurrence.",
"sentence": "Debug abends using SDSF, Abend-AID, and IBM Fault Analyzer; perform CICS trace analysis",
"similarity": 0.3513
}
],
"matched_count": null,
"matched_skills": null,
"role_id": 10,
"score": 0.3992,
"slug": "devops-engineer",
"total_count": null
}
],
"skill_match_roles": [
{
"display_name": "Data Engineer",
"kra_matches": null,
"matched_count": 1,
"matched_skills": [
"SQL"
],
"role_id": 2,
"score": 0.0476,
"slug": "data-engineer",
"total_count": 21
}
]
},
"stage4_decision": {
"alias_collision_detected": false,
"case": "E",
"chosen_role": null,
"confidence": 0.0,
"is_new_role": false,
"llm2_fired": false,
"llm2_reasoning": null,
"new_role_display_name": null,
"new_role_slug": null,
"queued": true,
"reasoning": "low_kra: top KRA 0.43 \u003c 0.45"
},
"stage5_updates": {
"centroid_n_after": null,
"centroid_updated": false,
"collision_log_id": null,
"new_kra_attached": null,
"new_skills_attached": [],
"queue_entry_id": 50,
"v3_pipeline_triggered": false,
"v3_role_slug": null,
"v3_run_id": null
}
}
API 2 — extract-details
{}
API 3 — final-role-output
{}
LLM Calls
Every model call made for this run, in pipeline order. Click a card to see the model's response.
Loading…