Software Development Engineer - Tejas

Overview

Build and run Sarvam's context engine, which gives enterprise AI agents searchable, citable access to their data and a memory that improves over time.

What you'll do

• Build and run the ingestion pipeline that parses, extracts and indexes large volumes of documents, and keep it reliable when files are messy and external services fail.
• Connect to databases and enterprise systems so agents can work with structured records as well as documents.
• Design how enterprise data is modelled, including the ontology, matching the same entity across sources, and tracing every value back to where it came from.
• Build the retrieval tools agents call, with search, filters and citations, and make them fast and cheap enough for agents to use heavily.
• Build memory for agents at the level of a user, a team and the whole organisation: how it is written, stored, retrieved and kept accurate over time.
• Run evals, find where answers go wrong, and keep iterating until quality improves.
• Work with product and forward-deployed engineers to turn what one customer needs into something the platform does for every customer.
• Write design docs and keep decisions documented.

What you'll need

• 3 to 5 years of experience.
• Built and run backend or data systems in production, and fixed them when they broke.
• Strong in at least one backend language.
• Good fundamentals in data modelling and PostgreSQL.
• Worked on long-running pipelines and made them safe to retry and recover.
• Worked on search or retrieval and can debug why the right result did not come back.
• Use AI coding tools every day and have a good sense of where they help and where they don't.
• Care about measuring quality and are comfortable building the evals to do it.

Nice to have

• Go experience.
• Experience with knowledge graphs, ontologies, entity resolution or structured extraction.
• Experience building memory for agents or LLM applications.
• Document processing, such as OCR, layout or table extraction.
• Connectors or change data capture for ERP, CRM or other enterprise systems.
• Building on MCP, or serving LLMs and embedding models in production.
• On-prem or air-gapped deployments.
• Experience at an early- or growth-stage startup.

Details

• Location: Bengaluru.
• Production stack: Go, Temporal, OpenSearch and Postgres.