Weekday AI

Founding AI Engineer

Delhi
Level
Mid

Not stated in the posting: salary, work type, visa.

Open. First seen 10 November 2026.

About the role

This role is for one of Weekday’s clients
Salary range: Rs 3000000 - Rs 9000000 (ie INR 30 - 90 LPA)

Min Experience: 6+ years
Location: NCR, India
JobType: full-time

We are looking for a Founding AI Engineer to architect, build, and scale production-grade autonomous AI agents capable of executing complex, multi-step real-world tasks.

The organisation is developing an AI-powered personal assistant designed to help users complete everyday tasks, from making calls and managing bookings to coordinating services and processing payments. The platform uses autonomous AI agents that can plan, execute, and verify outcomes rather than simply respond to user queries.

As a Founding AI Engineer, you will own the end-to-end Agentic AI infrastructure, spanning LLM orchestration, browser automation, persistent memory, workflow reliability, evaluation, and production deployment. This is a high-ownership opportunity to work directly with the founders and shape the core AI architecture and engineering direction.

Requirements

Key Responsibilities

Agentic AI Development

  • Design, develop, and deploy production-grade LLM agents capable of executing complex, multi-step tasks.
  • Implement advanced agent workflows involving multi-step tool calling, MCP servers, structured outputs, and context management.
  • Build robust LLM orchestration systems that enable agents to plan, reason, execute, and verify task outcomes.

Browser and Computer-Use Automation

  • Develop browser and computer-use agents using Playwright and Chrome DevTools Protocol (CDP).
  • Build automation capabilities for interacting with third-party websites, authentication flows, logins, and dynamic web interfaces.
  • Ensure reliable execution of complex workflows across external platforms.

Workflow Orchestration and Reliability

  • Design persistent memory systems and asynchronous task execution frameworks.
  • Implement scheduling, retries, state management, and failure-recovery mechanisms.
  • Build reliable workflows that can manage long-running tasks and handle unexpected execution failures.

Evaluation and Observability

  • Implement outcome verification, agent tracing, and trajectory logging.
  • Develop evaluation frameworks using LLM-as-a-Judge and regression testing.
  • Monitor agent performance, identify failure patterns, and continuously improve reliability and execution quality.

Backend Engineering and Infrastructure

  • Build scalable backend services and distributed agent systems using Python.
  • Design and deploy cloud-based infrastructure on AWS.
  • Ensure system performance, scalability, reliability, and maintainability in production environments.

Required Qualifications

  • Proven experience building and deploying production-grade Agentic AI systems, beyond basic chatbots or conventional RAG applications.
  • Strong expertise in LLM orchestration, multi-step tool calling, and autonomous agent workflows.
  • Hands-on experience with MCP servers, structured outputs, and context management.
  • Practical experience developing browser automation and computer-use agents using Playwright and CDP.
  • Strong Python backend engineering skills, including experience with asyncio and frameworks such as FastAPI or Django.
  • Understanding of agent architecture, persistent memory, asynchronous workflows, and failure-recovery mechanisms.
  • Experience with AI evaluation and observability tools such as Langfuse and OpenTelemetry.
  • Familiarity with LLM-as-a-Judge, trajectory logging, agent tracing, and regression testing.
  • Hands-on experience deploying scalable applications on AWS, including services such as ECS, SQS, Celery, and CloudWatch.
  • Knowledge of CI/CD practices and production infrastructure management.
  • Strong problem-solving skills and the ability to independently own technical architecture and execution.

Ideal Candidate Profile

  • A hands-on AI engineer who has built and operated autonomous agents in real-world production environments.
  • Comfortable working across the entire AI engineering stack, from agent architecture and orchestration to backend development and cloud deployment.
  • Experienced in building reliable systems that interact with external platforms and execute multi-step workflows.
  • Strong ownership mindset with the ability to make technical decisions and drive projects independently.
  • Comfortable working in a fast-paced startup environment and collaborating directly with founders.

Must-Have Skills

  • Agentic AI
  • LLM Orchestration
  • Multi-Step Tool Calling

What this role asks for

Standard for data science / ML roles

LLM · Python

Common in data science / ML postings at any company.

Compared with Weekday AI's other open jobs.

The team: Weekday's Client via platform HIRES STEADILY

This role is one of 564 open in Weekday's Client via platform. 343 were posted in the last 30 days and the oldest in September: a team that hires all year rather than one being built.

WHAT THE TEAM WORKS WITH, ACROSS ITS POSTINGS

Python (186 of 564), CI/CD (171 of 564), AWS (152 of 564), Azure (131 of 564), SQL (131 of 564), REST (115 of 564), GCP (112 of 564)

OTHER ROLES ON THIS TEAM

From the team and dates on Weekday AI's own job board.

Salary context

8 other open postings titled Founding AI Engineer state a salary: median USD 160,000 to USD 225,000 a year.

Similar jobs

More jobs like this

Is this your posting? Email [email protected] to have it removed.