AI Tooling Engineer - Remote

Zyte; India; Remote; INR 2,800,000 - 4,000,000; Full time

Job summary

Zyte, a globally distributed data-platform company, seeks an experienced Software Engineer for its Tooling team in India. You will build and ship production-grade AI tooling, connect internal systems, and develop agents and MCP servers used company-wide.

You will work with LangGraph, Langfuse, and major LLM APIs, ensuring scalable, secure cloud deployments. You will collaborate with cross-functional teams to translate requirements into robust software, optimize costs, and maintain high

Qualifications

• 3+ years shipping production software, primarily in Python.
• Experience with LangGraph and building AI agents.
• Hands-on with LLM APIs from major providers and cost/token optimization.
• Familiarity with MCP or similar tool protocols.
• Experience integrating APIs, SQL, and data warehouses.

Responsibilities

• Build platform features with the Tooling team from design to production.
• Integrate internal systems and SaaS tools via APIs into the platform.
• Develop agents and MCP servers used across the company.
• Ensure quality with evaluation sets, benchmarks, and tracing.
• Move proofs of concept to production tools in the cloud with security.
• Work with AI coding agents and maintain code quality with specs and reviews.
• Collaborate with teams to learn what to build next and explain outputs.

Skills

Python

LangGraph

Langfuse

LLM APIs

MCP

APIs

SQL

Data Warehouses

Cloud Infrastructure

CI/CD

Containers

IAM

Job description

About Us

At Zyte, we eat data for breakfast and you can eat your breakfast anywhere and work for Zyte. Founded in 2010, we are a globally distributed team of over 225 Zytans working from over 28 countries who are on a mission to enable our customers to extract the data they need to continue to innovate and grow their businesses. We believe that all businesses deserve a smooth pathway to data. For more than a decade, Zyte has led the way in building powerful, easy‑to‑use tools to collect, format, and deliver web data, quickly, dependably, and at scale. And today, the data we extract helps thousands of organizations make smarter business decisions, secure competitive advantage, and drive sustainable growth. Today, over 3,000 companies and 1 million developers rely on our tools and services to get the data they need from the web. This role sits in Zyte's Tooling team, working side by side with our Principal Engineer in Tooling on an internal agentic platform: one place that brings together what the company knows, today spread across many systems, so that people and their AI agents get that context in one place, each seeing only what they are allowed to see.

Roles & Responsibilities:

• Build the platform with the Principal Engineer in Tooling: new capabilities every week, from design to production.
• Connect new internal systems and SaaS tools to the platform: their APIs and data, how they fit a shared model, and who may see what.
• Build agents and the tools they use, including MCP servers that agents across the company can call, and the context they need to answer well.
• Own quality: evaluation sets and benchmarks, tracing, cost per answer, and fixing what users run into.
• Turn proofs of concept into internal tools that run in production in the cloud, with security and access done properly.
• Build with AI coding agents as the main way of working, with the specs, tests and reviews that keep the code sound.
• Contribute to company-wide AI tooling initiatives: evaluating and standardising internal AI tools, cost and usage tracking, and agreed standards for AI-built internal apps; help other teams build on the platform.
• Talk with the people who use the platform, across the company, to learn what to build next, and explain what was built to technical and non-technical audiences.
• 3+ years building and shipping production software, mostly in Python, with relational databases.
• Has built and shipped with LangGraph at least one agent that real people use: tool calling, retrieval and embeddings, prompt and context design.
• Hands-on experience with LLM APIs from the main providers, cost and token optimisation.
• Hands-on with MCP or similar tool protocols, as a server and as a client.
• Evaluates AI systems properly: test sets, LLM-as-judge, regressions when a prompt or a model changes; tracing and observability with Langfuse or similar.
• Integrates APIs and data: SaaS APIs, SQL, data warehouses.
• Experience with cloud infrastructure (Google Cloud and/or AWS): containers, managed databases, identity and access, CI/CD.
• Uses AI coding agents every day and knows how to keep their output in check.