Zepto at a glance

Founded in 2021

More than 1000

Employee reviews

Overall

3.7

Work-Life Balance

2.8

Salary and Advantages

3.8

Company Culture

3.3

Career Growth

3.6

Diversity and Inclusion

3.8

Will Recommend to Friends

3

Senior Context Engineer

Zepto

Bangalore5-9 Years

Apply to Zepto

Apply to Zepto

About Zepto

Our Story

Founded in 2021 by Aadit Palicha and Kaivalya Vohra, Zepto is on a mission to save you time making every second count towards life's real joys. Our platform has revolutionized rapid commerce in India with cutting-edge technology and strategically optimized delivery hubs. Zepto offers an extensive range of 45,000+ products, from fresh groceries to electronics, beauty essentials, apparels, toys and more, delivering across 50+ cities in minutes*.

Zepto

Caf extends our commitment to convenience, featuring a curated menu of over 200 fresh items.

Engineering @ Zepto

Building for scale, rapid iterative development, and customer-centric product thinking at each step define every day for a Zepto engineer. If building technology that impacts millions, brainstorming with some of the best minds in the country, executing at lightning speed, product-driven thinking, and owning your work from start to finish excites you, then Zepto is the right place for you.

About Company

Write a description for your company

Function: Software Engineering → Backend Development, Other Software Development, Data Science and Analysis → Data Science / Machine Learning

- PostgreSQL
- Postgres
- RAG
- TypeScript
- +2 more
- context
- retrieval

Responsibilities

- Build and own the system that captures everything Sonic knows about each client's brand guidelines, design language, copy archives, past creative, and other textual assets and makes it queryable in milliseconds.
- Build and own the system that pulls live data from each client's existing marketing stack campaign tools (e. g., Braze, Customer.io ), product analytics (e. g., Mixpanel, Amplitude), knowledge bases (e. g., Notion), communication channels (e. g., Slack), and behavioral data (e. g., Fathom) and normalizes it into context the agent can reason about. OAuth, rate limits, schema drift, and new integrations as the product grows.
- Build and own the system that brings non-textual context into Sonic images today, with video and other modalities to follow through embedding and retrieval choices appropriate to each modality.
- Build the loop that lets Sonic learn from itself, capturing what the agent did, what worked, what didn't, and the patterns across tool calls and user interactions, then feeding those learnings back as context that improves future runs.
- Design the end-to-end context pipeline ingestion, chunking, vectorisation, storage, retrieval, and delivery with predictable latency, cost, and quality.
- Build the evaluation framework that measures whether context is actually doing its job: retrieval-quality metrics, agent-quality regression tests, and dashboards the team uses to catch problems before users do. You ship this yourself; you do not delegate it.
- Set the architectural direction for context across the platform patterns the team builds on, decisions documented in writing, and junior engineers contributing under your direction.
- Author RFCs (Request for Comments), end-to-end written design documents that specify the problem, alternatives considered, trade-offs, the decision, and what is explicitly not being built. Sharp enough that another engineer or an AI agent could build the right thing without you in the room.

- Mentor a junior engineer or intern to ship-readiness on a scoped piece of the context surface.
- Ship through AI agents. Write specifications Claude (or equivalent) can execute against, review the output critically, and ship the result. Propel engineers do not measure their value in lines of code typed.
- Collaborate closely with the engineers who consume your context API, shaping what you produce to fit how the agent actually uses it.

Requirements

- 5-7 years of total engineering experience, with at least 2-3 years on production context pipelines, retrieval-augmented systems, or retrieval at scale.
- Has shipped a production retrieval or context system and run the evaluations that prove it works. Both halves are required; we will ask for the specific evaluation design and what it caught.
- Hands-on builder.

You can sit down and ship the evaluation framework yourself this week, not delegate it.

- Strong systems thinker. Opinions on vectorisation choices, chunking strategy, retrieval ranking, hybrid search, and cost/latency trade-offs and the ability to defend them.

- Has built or owned at least two integration connectors end-to-end (OAuth, rate limits, normalisation).
- Comfortable in our stack: TypeScript, Node.js, PostgreSQL, vector storage (pgvector or equivalent).
- Strong adjacent stacks accepted if the ramp story is credible.
- Written communication strong enough to author RFCs that another engineer or an AI agent can build from without you in the room.
- AI-augmented engineering as a first-class part of your loop. If working through Claude (or equivalent) feels uncomfortable to you,



this role is not a fit.
- Smart and curious first-principles reasoning, comfortable in ambiguity, learns the next thing fast.

Zepto Office and Product Photos

0 && (!isOpenedInMobile || showSections.photos)" class="office-photos-block ng-scope">

Job posted by

Monika Srivastava

Manager - Staffing at Pylon Management Consulting

Similar jobs

AI Engineer

Clair Labs

Bangalore

Senior Software Engineer The Walt Disney Company

Bangalore

Senior Software Developer

Scopely

Bangalore

Senior Context Engineer

Amazon

Bangalore

Senior Software Engineer

BetterPlace

Bangalore

Senior Context Engineer

Dify

Bangalore

Senior Product Software Engineer The Walt Disney Company

Bangalore

Staff Product Development Engineer The Walt Disney Company

Bangalore

Senior Backend Engineer - Python

Qure.ai

Bangalore

Senior Software Engineer

Netsmart

Bangalore

Function: Software Engineering → Backend Development, Other Software Development, Data Science and Analysis → Data Science / Machine Learning

- PostgreSQL
- Postgres
- RAG
- TypeScript
- +2 more
- context
- retrieval

Responsibilities

- Build and own the system that captures everything Sonic knows about each client's brand guidelines, design language, copy archives, past creative, and other textual assets and makes it queryable in milliseconds.
- Build and own the system that pulls live data from each client's existing marketing stack campaign tools (e. g., Braze, Customer.io ), product analytics (e. g., Mixpanel, Amplitude), knowledge bases (e. g., Notion), communication channels (e. g., Slack), and behavioral data (e. g., Fathom) and normalizes it into context the agent can reason about. OAuth, rate limits, schema drift, and new integrations as the product grows.
- Build and own the system that brings non-textual context into Sonic images today, with video and other modalities to follow through embedding and retrieval choices appropriate to each modality.
- Build the loop that lets Sonic learn from itself, capturing what the agent did, what worked, what didn't, and the patterns across tool calls and user interactions, then feeding those learnings back as context that improves future runs.
- Design the end-to-end context pipeline ingestion, chunking, vectorisation, storage, retrieval, and delivery with predictable latency, cost, and quality.
- Build the evaluation framework that measures whether context is actually doing its job: retrieval-quality metrics, agent-quality regression tests, and dashboards the team uses to catch problems before users do. You ship this yourself; you do not delegate it.
- Set the architectural direction for context across the platform patterns the team builds on, decisions documented in writing, and junior engineers contributing under your direction.
- Author RFCs (Request for Comments), end-to-end written design documents that specify the problem, alternatives considered, trade-offs, the decision, and what is explicitly not being built. Sharp enough that another engineer or an AI agent could build the right thing without you in the room.

- Mentor a junior engineer or intern to ship-readiness on a scoped piece of the context surface.
- Ship through AI agents. Write specifications Claude (or equivalent) can execute against, review the output critically, and ship the result. Propel engineers do not measure their value in lines of code typed.
- Collaborate closely with the engineers who consume your context API, shaping what you produce to fit how the agent actually uses it.

Requirements

- 5-7 years of total engineering experience, with at least 2-3 years on production context pipelines, retrieval-augmented systems, or retrieval at scale.
- Has shipped a production retrieval or context system and run the evaluations that prove it works. Both halves are required; we will ask for the specific evaluation design and what it caught.
- Hands-on builder.

You can sit down and ship the evaluation framework yourself this week, not delegate it.

- Strong systems thinker. Opinions on vectorisation choices, chunking strategy, retrieval ranking, hybrid search, and cost/latency trade-offs and the ability to defend them.

- Has built or owned at least two integration connectors end-to-end (OAuth, rate limits, normalisation).
- Comfortable in our stack: TypeScript, Node.js, PostgreSQL, vector storage (pgvector or equivalent).
- Strong adjacent stacks accepted if the ramp story is credible.
- Written communication strong enough to author RFCs that another engineer or an AI agent can build from without you in the room.
- AI-augmented engineering as a first-class part of your loop. If working through Claude (or equivalent) feels uncomfortable to you, this role is not a fit.
- Smart and curious first-principles reasoning, comfortable in ambiguity,



learns the next thing fast.

Zepto Office and Product Photos

0 && (!isOpenedInMobile || showSections.photos)" class="office-photos-block ng-scope">

Our Story

Founded in 2021 by Aadit Palicha and Kaivalya Vohra, Zepto is on a mission to save you time making every second count towards life's real joys. Our platform has revolutionized rapid commerce in India with cutting-edge technology and strategically optimized delivery hubs. Zepto offers an extensive range of 45,000+ products, from fresh groceries to electronics, beauty essentials, apparels, toys and more, delivering across 50+ cities in minutes*.

Zepto

Caf extends our commitment to convenience, featuring a curated menu of over 200 fresh items.

Engineering @ Zepto

Building for scale, rapid iterative development, and customer-centric product thinking at each step define every day for a Zepto engineer. If building technology that impacts millions, brainstorming with some of the best minds in the country, executing at lightning speed, product-driven thinking, and owning your work from start to finish excites you, then Zepto is the right place for you.

Responsibilities

- Build and own the system that captures everything Sonic knows about each client's brand guidelines, design language, copy archives, past creative, and other textual assets and makes it queryable in milliseconds.
- Build and own the system that pulls live data from each client's existing marketing stack campaign tools (e. g., Braze, Customer.io ), product analytics (e. g., Mixpanel, Amplitude), knowledge bases (e. g., Notion), communication channels (e. g., Slack), and behavioral data (e. g., Fathom) and normalizes it into context the agent can reason about. OAuth, rate limits, schema drift, and new integrations as the product grows.
- Build and own the system that brings non-textual context into Sonic images today, with video and other modalities to follow through embedding and retrieval choices appropriate to each modality.
- Build the loop that lets Sonic learn from itself, capturing what the agent did, what worked, what didn't, and the patterns across tool calls and user interactions, then feeding those learnings back as context that improves future runs.
- Design the end-to-end context pipeline ingestion, chunking, vectorisation, storage, retrieval, and delivery with predictable latency, cost, and quality.
- Build the evaluation framework that measures whether context is actually doing its job: retrieval-quality metrics, agent-quality regression tests, and dashboards the team uses to catch problems before users do. You ship this yourself; you do not delegate it.
- Set the architectural direction for context across the platform patterns the team builds on, decisions documented in writing, and junior engineers contributing under your direction.
- Author RFCs (Request for Comments), end-to-end written design documents that specify the problem, alternatives considered, trade-offs, the decision, and what is explicitly not being built. Sharp enough that another engineer or an AI agent could build the right thing without you in the room.

- Mentor a junior engineer or intern to ship-readiness on a scoped piece of the context surface.
- Ship through AI agents. Write specifications Claude (or equivalent) can execute against, review the output critically, and ship the result. Propel engineers do not measure their value in lines of code typed.
- Collaborate closely with the engineers who consume your context API, shaping what you produce to fit how the agent actually uses it.

Requirements

- 5-7 years of total engineering experience, with at least 2-3 years on production context pipelines, retrieval-augmented systems, or retrieval at scale.
- Has shipped a production retrieval or context system and run the evaluations that prove it works. Both halves are required; we will ask for the specific evaluation design and what it caught.
- Hands-on builder.

You can sit down and ship the evaluation framework yourself this week, not delegate it.

- Strong systems thinker. Opinions on vectorisation choices, chunking strategy, retrieval ranking, hybrid search, and cost/latency trade-offs and the ability to defend them.

- Has built or owned at least two integration connectors end-to-end (OAuth, rate limits, normalisation).
- Comfortable in our stack: TypeScript, Node.js, PostgreSQL, vector storage (pgvector or equivalent).
- Strong adjacent stacks accepted if the ramp story is credible.
- Written communication strong enough to author RFCs that another engineer or an AI agent can build from without you in the room.
- AI-augmented engineering as a first-class part of your loop. If working through Claude (or equivalent) feels uncomfortable to you, this role is not a fit.
- Smart and curious first-principles reasoning, comfortable in ambiguity, learns the next thing fast.
- Jobs in Bangalore
- Jobs in Delhi / NCR
- Jobs in Hyderabad
- Jobs in Mumbai
- Software Engineering Jobs
- Marketing Jobs
- Sales Jobs
- Internship Jobs
- Post Your Jobs
- Success Stories
- Product Academy
- Resources
- Workscape
- About
- Privacy
- Terms
- Help Center
- Contact Us

One of our representatives will contact you shortly.

📌 Senior Context Engineer (Bengaluru)
🏢 Nexus Venture Partners
📍 Bengaluru