Software Development Engineer - Tejas

Bengaluru. Posted 20 days ago

The role

You will build and run the ingestion pipeline, connect to enterprise systems, and design data models. You will also build retrieval tools and memory for agents to improve quality through evals.

What you will do

Build and run the ingestion pipeline that parses, extracts and indexes large volumes of documents.
Connect to databases and enterprise systems.
Design how enterprise data is modelled, including the ontology and tracing values to sources.
Build retrieval tools with search, filters and citations.
Build memory for agents at the level of a user, a team and the whole organisation.
Run evals to improve quality.
Work with product and forward-deployed engineers to scale customer needs to the platform.
Write design docs and keep decisions documented.

Required qualifications

3 to 5 years of experience.
Built and run backend or data systems in production.
Strong in at least one backend language.
Good fundamentals in data modelling and PostgreSQL.
Worked on long-running pipelines.
Worked on search or retrieval.
Use AI coding tools every day.
Comfortable building evals to measure quality.

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

About the company

Sarvam is India's leading full-stack AI company, building sovereign AI infrastructure and applications purpose-built for India. Headquartered in Bengaluru, it builds foundational models for Indian languages, enterprise AI platforms, and voice-first AI agents.