Frontend Engineer, Vision

About Sarvam Sarvam is building the bedrock of Sovereign AI for India. The company is developing India's full-stack sovereign AI platform, building across research, models, infrastructure and applications with a singular focus on making AI genuinely work for India. Sarvam works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures. Sarvam partners with India's leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC. About the Team Sarvam's research teams build our own vision-language models for OCR and structured extraction. This team builds everything around them — the serving harness that turns a 3B or 30B in-house model into a production document intelligence platform. The bet is specific: with the right harness — routing, decomposition, retries, verification, ensembling, layout awareness, confidence calibration — a small sovereign model should match or beat what teams today get from frontier hosted models like Gemini Flash, at a fraction of the cost and fully within India. Closing that gap is an engineering problem, and it is this team's problem. We run against the full messiness of Indian documents at population scale: PAN and Aadhaar, bank statements, GST filings, insurance and medical reports, 60-page contracts, legal filings and RFPs — across languages, scan quality, and layouts that were never designed to be machine-read. Stack: Go, Python, Temporal, REST, Kubernetes, PostgreSQL, Redis, object storage, OpenTelemetry-based observability. About the Role Document intelligence is only trustworthy if a human can see what the model saw. You will build the interfaces where that happens: document viewers with field-level grounding, review and correction workflows, extraction schema builders, evaluation dashboards, and the developer-facing console our enterprise customers use to run pipelines at scale. These are dense, stateful, performance-sensitive UIs — rendering 100-page PDFs with overlaid bounding boxes, streaming results as pages complete, letting a reviewer correct a field and push that correction back into the loop. The quality of this surface directly determines how much our customers trust the system. You will be the frontend owner for the team, working closely with backend and applied AI engineers rather than against a finished spec. What You'll Do Build the document review experience: PDF and image rendering, page navigation, bounding-box overlays, confidence highlighting, side-by-side source-to-extraction linking Build human-in-the-loop correction workflows — fast keyboard-driven review, field-level edit, approve/reject queues — and wire corrections back into the evaluation loop Build the extraction schema designer: let users define, test, and version the structured output they want from a document type Build internal evaluation and observability dashboards — accuracy by field and document type, latency and cost breakdowns, model comparison views Handle real-time and