← Back to history

Pipeline run

fa391964-09d6-4907-a6f0-e2bbd95623ea

Pipeline LLM cost (USD)

API 1: $0.0018 API 2: $0.0000 API 3: $0.0000 Total: $0.0018

Client output enrichment

v2 Skill cluster · Nature of work · AI index · Tech stack maturity · Evidence · KRA description

SPARSE JD

Nature of work

—

no_db_connection

Tech stack maturity

Mainstream Modern

AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)

0.20 / 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): AI

Evidence — skills matched in JD (0)

No skills extracted

Skill cluster (0 dimension groups, role-scoped)

No dimension groups computed for this JD.

Status: completed Created: 2026-05-24T21:57:39.470497Z Updated: 2026-05-24T21:57:39.534040Z API 3 duration: 25 ms

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

—

slug: — · id: — · source: llm

Stage 1 marked JD_type=fail (unparseable)

Resolution: human_review_required — role not in DB; role↔dimension links may be deferred.

New skills

Skill↔dim saved

Role↔dim saved

Skipped

Job description

Role : Software Engineer
ALLEN Digital  Feb 2024 – Present  Senior Software Engineer (SDE3) React, Next.js, Node.js, Vite, Rollup, Redis, AWS, Firebase  • Led a team of 8 engineers to design and deliver SpectraVerse, an org-wide SDK adopted across 4–6 product teams (subject  tests, live classes, learning content, active learning, interactive 3D). Drove cross-team architecture reviews, deﬁned component  interfaces, established CI/linting automation to eliminate integration rework, and mentored engineers on system design  and API design practices.  • Built Streamlite as SpectraVerse’s ﬂagship use case — a real-time interactive HTML streaming system for live classes supporting  5,000+ concurrent students/day, reducing bandwidth from 2 GB/hr to 50 MB/hr (96% reduction) while delivering  slides, audio, video, whiteboard, and 3D content.  • Architected the content editor platform — built a high-availability cache server (Express + Redis) achieving  >99.99% uptime, reducing page load from 3–4 s to ∼300 ms. Led a team of 10 engineers.  • Drove deep performance optimisation of the content platform — refactored rendering logic, overhauled Vite bundle splitting and  loading strategy — achieving 2× improvement in overall page performance and reducing LCP from 10 s to 5.5 s on  dynamically rendered content. Boosted Lighthouse score from 60 to 95+.  • Content editor enabled ∼20 SEO pages/day/head, drove Google search ranking 9.1 → 4.5 and 70× growth in impres-  sions within 1 year — directly accelerating organic user acquisition at scale.  • Led migration of 80 lakh Doubtnut pages to ALLEN’s domain — architected static HTML generation served entirely from  S3 via CDN, eliminating the dedicated Doubtnut server and consolidating all traﬃc to allen.in. Resulted in 5× growth  in domain impressions, signiﬁcantly strengthening domain authority and organic search credibility.  Wobot AI  May 2023 – Oct 2023  Senior Frontend Developer II (Consultant) React, TypeScript, Component Libraries  • Architected a modular React component library for an AI-driven video intelligence platform (CCTV / Drive-Thru order man-  agement), accelerating feature delivery by 30% while improving UI consistency across engineering teams.  • Deﬁned component contracts and API integration patterns, established Agile practices, and introduced integration testing —  signiﬁcantly improving platform reliability and reducing regression across releases.  QuickSell  Jul 2021 – Apr 2023  Senior Frontend Developer React, WebSockets, Web Workers, Node.js  • Designed and built a CRM from scratch — deﬁned CRUD API contracts and data schemas for contact and lead management,  implemented real-time updates via WebSockets/webhooks, and built a bot-builder for automated replies. Served 100K+ daily  active users.  • Engineered frontend performance via virtualization, Web Workers, and client-side caching — signiﬁcantly improving responsive-  ness for 100K+ DAU; introduced integration testing for API reliability and lead source tracking in the contact chat box to  support sales analysis.  Walmart Labs India  Software Engineer II Angular, Spring Boot, SQL  Jun 2020 – Jul 2021  • Modernised a critical web platform for 500+ distribution centers by adopting modular Angular component patterns —  improving UX, system performance, and codebase scalability. Increased unit test coverage from 0% to 95% across services.  • Built Spring Boot + SQL backend with RESTful APIs for resource analytics consumed by 50+ managers; designed reusable  data models and graphical reporting modules for operational insights.  Innoplexus  Jun 2018 – Mar 2020  Member of Technical Staﬀ React, Redux, Node.js, Spring Boot, D3.js, MySQL, MongoDB  • Built full-stack applications (React + Node.js + Spring Boot) across 2 products and 6 applications using agile methodology;  developed a conﬁgurable drag-and-drop dashboard rendering engine and 12+ D3.js data visualisation dashboards.  EDUCATION  Indian Institute of Technology, Roorkee  B.Tech, Polymer Science and Technology  2014 – 2018  CGPA: 7.2 / 10  SKILLS  Tech Stack  Engineering  React, Next.js, TypeScript, JavaScript, Angular, HTML/CSS, SCSS, D3.js, Vite, Node.js, Express, Spring Boot  System Design, API Contract Design, Distributed Systems, SDK Architecture, Redis, MongoDB, MySQL, AWS,  Firebase, S3, CDN, SSR, Caching, WebSockets, Web Workers, Rollup, Rolldown, Webpack, Git, Jest, SEO

Library artifacts (this run)

No artifact rows for this run.

nano JD Parser — gpt-4.1-nano click to toggle

JD type fail

Show raw JSON

{
  "JD_type": "fail",
  "archetype_override_applied": true,
  "archetype_override_matched_skills": [
    "Redis",
    "Integration testing",
    "MongoDB",
    "AWS",
    "Agile",
    "SEO",
    "Vite",
    "Webpack",
    "Rollup",
    "Lighthouse",
    "virtualization",
    "Git",
    "Frontend",
    "JavaScript",
    "APIs",
    "Analytics",
    "Distributed Systems",
    "CSS",
    "MySQL",
    "React",
    "Angular",
    "Next.js",
    "Redux",
    "TypeScript",
    "WebSockets",
    "Express",
    "Spring Boot",
    "Jest",
    "Node.js",
    "API",
    "API Integration",
    "Spring",
    "Role",
    "SQL",
    "HTML",
    "Dashboard"
  ],
  "role_archetype": "Engineering"
}

API 1 — extract-from-jd click to toggle

{
  "final_skills": [],
  "jd_role": {
    "display_name": "\u2014",
    "rationale": "Stage 1 marked JD_type=fail (unparseable)",
    "role_aliases": [],
    "role_archetype": "Engineering",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "fail",
    "archetype_override_applied": true,
    "archetype_override_matched_skills": [
      "Redis",
      "Integration testing",
      "MongoDB",
      "AWS",
      "Agile",
      "SEO",
      "Vite",
      "Webpack",
      "Rollup",
      "Lighthouse",
      "virtualization",
      "Git",
      "Frontend",
      "JavaScript",
      "APIs",
      "Analytics",
      "Distributed Systems",
      "CSS",
      "MySQL",
      "React",
      "Angular",
      "Next.js",
      "Redux",
      "TypeScript",
      "WebSockets",
      "Express",
      "Spring Boot",
      "Jest",
      "Node.js",
      "API",
      "API Integration",
      "Spring",
      "Role",
      "SQL",
      "HTML",
      "Dashboard"
    ],
    "role_archetype": "Engineering"
  },
  "rejected": true,
  "rejection_reason": "Stage 1 marked JD_type=fail (unparseable)",
  "run_id": null,
  "stage3_signals": null,
  "stage4_decision": null,
  "stage5_updates": null
}

API 2 — extract-details

{
  "alias_matches": [],
  "candidate_roles": [],
  "chosen_role": {
    "display_name": "\u2014",
    "id": null,
    "rationale": "Stage 1 marked JD_type=fail (unparseable)",
    "role_archetype": "Engineering",
    "slug": "",
    "source": "llm"
  },
  "dimensions": [],
  "input_final_skills": [],
  "input_llm_skills": [],
  "new_aliases_persisted": 0,
  "run_id": "fa391964-09d6-4907-a6f0-e2bbd95623ea",
  "skills_detail": [],
  "unmatched_skills": []
}

API 3 — final-role-output

{
  "chosen_role": {
    "display_name": "\u2014",
    "id": null,
    "rationale": "Stage 1 marked JD_type=fail (unparseable)",
    "role_archetype": "Engineering",
    "slug": "",
    "source": "llm"
  },
  "chosen_role_resolution": "human_review_required",
  "final_input_skills": [],
  "llm_cost_api1_usd": null,
  "llm_cost_api2_usd": null,
  "llm_cost_api3_usd": null,
  "llm_cost_total_usd": null,
  "persistence": {
    "items": [],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 0
  },
  "planner_output": null,
  "run_id": "fa391964-09d6-4907-a6f0-e2bbd95623ea"
}

LLM Calls

Every model call made for this run, in pipeline order. Click a card to see the model's response.

Loading…