Shagun Khemka, Senior Software Engineer at JioHotstar

Hey, I'm Shagun Khemka.

I build backend platforms that stay fast under heavy load, and production AI systems that stay cheap and correct.

Senior Software Engineer at JioHotstar, working on the subscriptions and entitlements platform. Previously FamPay (YC S19) and Instamojo. Based in Mumbai.

GitHub ↗LinkedIn ↗X ↗Email

Experience

JioHotstarSenior Software Engineer, Backend
  • Architected and own the P0 entitlement read path at ~50K RPS, holding P99 SLAs on ~20% fewer pods
  • Re-architected purchase and upgrade flows for ~20% revenue growth; team won “Astral Team Award” (2026)
  • Led the cross-team migration of 14M+ JioCinema subscribers
  • Helped build the JioCinema entitlement service serving user attributes to core services (Go, Spanner, Redis); team won “Gangstar of the Quarter” (2024)
  • ~20% compute savings from a Graviton + Java 21 migration, packaged as Claude and Codex agent skills for self-serve rollout
  • IPL on-call at 30M+ concurrent viewers · LLD/HLD hiring panelist (20+ interviews)
2024 – now
FamPay (YC S19)Software Engineer, Backend
  • Led a team of four on FamCard: 5M+ virtual cards, ₹10M+ daily transactions, ~30% lower delivery cost
  • Built recharge, gift card and bill-payment products, around 60% of company revenue
  • 30+ backend interviews; onboarded new engineers and mentored 5+ interns and juniors into full-time roles
2020 – 2024
InstamojoSoftware Engineer, Backend
  • Automated merchant onboarding, cutting KYC resubmissions by ~25%
  • Built reseller product ingestion that onboarded ~15K products in its first month; converted from intern to full-time
2019 – 2020

Projects

Document extraction platformin production

private

An LLM pipeline, built for a logistics ERP software company, that turns scanned, handwritten consignment notes into validated, structured data. I designed, built and run it on my own.

  • Evals pick the model: every model, prompt or provider change is scored field by field against a labelled golden set before it ships. I evaluated Claude, GPT, Gemini, Qwen, Mistral and Sarvam side by side, and the cheapest models that got every ledger-critical field right (total amount, invoice value and actual weight) went to production.
  • Phased model rollout: production runs Gemini 3.8 Flash and GPT-6 Luna, switched tenant by tenant from the admin panel with no redeploy. On the latest eval, GPT-6 Luna is 8× cheaper and ~45% faster than Gemini Flash, with those ledger-critical fields at 100%.
  • Guardrails and accept policy: GSTIN checksum and state checks, date and total reconciliation, and fuzzy station matching. A document is auto-added only when every mandatory field passes; otherwise it's flagged for human review with the exact fields named.
  • Gateway, cost and observability: Anthropic, OpenAI, Gemini, Mistral and Sarvam sit behind one interface, and tenants can bring their own keys. Every call is metered per tenant, and dashboards track cost per document and latency.
Model selectionEvalsStructured outputsHuman-in-the-loopLLM cost metering

Python · Django · Postgres · GPT / Gemini (production) · Claude, Qwen, Mistral, Sarvam (evaluated) · Pulumi · Prometheus + Grafana

ConsumerBuddyprivate beta

consumerbuddy.in ↗

An AI product that helps Indian consumers draft and file consumer-court complaints without a lawyer. I built and run it end to end.

  • Vision and tool use: Claude reads uploaded evidence (PDFs and photos) to write court-format annexure descriptions, and uses its web-search tool to find the opposite party's registered address and legal contacts.
  • Runtime model routing: a different model per task (Sonnet drafts, Haiku handles lookups and vision), configurable per user cohort from the admin panel without a redeploy. Each paid document pins the model plan it was drafted with, so re-renders are reproducible.
  • Cost and abuse controls: a per-call cost ledger in INR, hourly and daily AI caps per user, and input limits on every AI feature.
  • LLM observability and legal review: calls, tokens, latency, errors and INR cost tracked per feature, provider and model. Drafts go to a consumer-law advocate for sign-off before public launch.
Multi-model routingVisionTool useCost controlsLLM observability

Next.js · FastAPI · Postgres · Claude Sonnet + Haiku (production) · GPT, Gemini, Sarvam (integrated) · AWS via Pulumi · Prometheus + Grafana

Open source, education and certifications → Background