Back to jobs
Since public launch, Emergent has reached $50M ARR in 7 months. 5M+ users across 190+ countries have built 6M+ applications on Emergent. We’ve raised $100M, backed by Khosla Ventures, SoftBank, Google, Lightspeed, Prosus, Together, and Y Combinator.
We’re solving the hard part of AI-driven software creation: correctness, reliability, security, and scale in real production systems. The team is built by repeat founders, Olympiad medalists, IIT & IIM alumni, and leaders from Google, Amazon, and Dropbox.
We’re hiring builders who want ownership, speed, and impact at global scale.
Coding Agent Architect
Bangalore
Emergent builds autonomous coding agents that replace traditional software development by generating, testing, and deploying production applications directly from plain-language intent. Our systems run in production at global scale and are used to build millions of real applications.
Since public launch, Emergent has reached $50M ARR in 7 months. 5M+ users across 190+ countries have built 6M+ applications on Emergent. We’ve raised $100M, backed by Khosla Ventures, SoftBank, Google, Lightspeed, Prosus, Together, and Y Combinator.
We’re solving the hard part of AI-driven software creation: correctness, reliability, security, and scale in real production systems. The team is built by repeat founders, Olympiad medalists, IIT & IIM alumni, and leaders from Google, Amazon, and Dropbox.
We’re hiring builders who want ownership, speed, and impact at global scale.
The Role:
We’re building AI coding agents that can plan, build, test, and ship real software. Your role is to turn LLM model and system capabilities into measurable, shippable improvements in agent performance. You will own experimentation and shipping decisions - what we try, how we measure better, what goes live, and what gets rolled back.
What You’ll Do :-
- Develop deep intuition for LLM and agent behavior, identifying failure modes and regressions.
- Define and run high-leverage experiments to improve agent quality, reliability, and code outcomes.
- Ship improvements with clear metrics, evaluation gates, staged rollouts, and rollback criteria.
- Define evaluation frameworks and work with engineering teams to measure agent quality at scale.
- Drive initiatives around context engineering, memory systems, and frontier agent capabilities.
- Think like the agent — continuously making it smarter, more reliable, and more useful.
Who You Are :-
- 5+ years of software engineering experience with end-to-end ownership.
- Strong technical depth paired with sharp product intuition.
- Comfortable working with metrics, experimentation, SQL, and/or Python.
- Able to thrive in ambiguity and move fast with rigor.
- Hands-on and up-to-date with emerging AI research and industry trends
Apply for this job
*
indicates a required field