Leads the team this role joins
Heads the group this role sits in
In-house, owns the opening
From your own Gmail and LinkedIn.
About the role
This is a mid-level, full-time AI engineering role based in Gurugram, India, for engineers with at least three years of experience who want to join an early-stage startup. The job is in-office, six days a week. The engineer owns the architecture and development of AI agents that complete multi-step tasks on their own, including browser and computer-use agents that work across third-party websites. The startup is building products from zero to one, so the role also carries deployment, scaling and evaluation responsibilities with direct access to the founders.
What you’ll do
- Own the architecture and development of AI agents that take a user request and complete multi-step tasks independently.
- Build and improve the agent harness, including tool calling, MCP servers, memory, context management and structured outputs.
- Develop browser and computer-use agents that handle login flows, OTP verification and dynamic pages.
- Build workflows that recover from failures, handle incomplete tasks and confirm that an action was completed.
- Design scheduling systems that keep tasks running across several days and resume when needed.
- Build evaluation frameworks for agent performance, reliability and accuracy.
- Set up observability through trajectory logging, replayable runs, LLM-as-judge scoring and regression testing.
- Improve agent performance using real task outcomes and feedback.
- Make critical technical and product decisions with the founders.
What they’re looking for
- 3+ years in AI engineering, machine learning engineering, applied AI or related roles.
- Currently working at a product-based company.
- Experience in a founding or early-stage engineering team, ideally taking a product from zero to one.
- Hands-on experience running production LLM agents, including multi-step tool calling, MCP servers, context management, memory, structured outputs and streaming.
- Experience building browser or computer-use agents with Playwright, CDP or similar tools.
- Experience building agent evaluation and observability systems.
- Strong Python, including asyncio and FastAPI or Django.
- Production AWS experience, including ECS, SQS or Celery workers, autoscaling, CloudWatch and CI/CD.
- High ownership, high agency and the ability to work independently.
- Willingness to work in-office in Gurgaon six days a week.
What’s on offer
- A full-time, in-office role in Gurgaon, six days a week.
- Direct work with the founders on technical and product decisions.
Skills
Questions about this role
Is this role remote?
No. It is an in-office role in Gurgaon, six days a week.
How many years of experience do I need?
At least three years of professional experience in AI, ML or applied AI engineering.
What is the interview process?
A technical screening, an AI and LLM engineering round, a system design round, a founders round and a culture fit round.