LEAD SOFTWARE ENGINEER • AI AUTOMATION • LLM • PYTHON

Lead Software Engineer – AI Automation

AI Automation Engineer

Build and ship production-grade AI automations that combine Python, REST APIs, data stores and Large Language Models to transform enterprise operations at scale.

Experience: 6+ Years Python
Focus: AI Automation
Location: Remote
Base: Bangalore / Pune
Work: Production Engineering
Apply Now ↗

Who Is This Role For?

This role is designed for a strong production-focused software engineer who can turn business process specifications into reliable, monitored and scalable AI-powered automation systems.

01

Production Python Engineer

Experienced in building Python systems that run in production, handle failures, integrate external services and evolve through continuous delivery.

02

AI Automation Engineer

Comfortable integrating LLMs into real workflows using prompts, structured outputs, validation and quality thresholds.

03

Integration-Focused Engineer

Strong with REST APIs, authentication, rate limits, pagination, data stores, SQL and troubleshooting complex integrations.

04

Agentic AI Builder

Interested in designing multi-step AI workflows involving tools, memory, planning, orchestration and evaluation.

Build Automation That Works in Production

The role sits within Circana's AI & Automation transformation program. Engineers take process specifications and convert them into deployed, monitored systems that deliver measurable operational improvements.

Understand Analyze process specifications
Design Define technical architecture
Build Develop Python automation
Deploy Release into production
Monitor Stabilize and improve

What You Will Do

01

Translate Process Specifications Into Technical Solutions

Design technical approaches covering data flow, integrations, LLM components, error handling and human-in-the-loop controls.

02

Build Python-Based Automations

Develop production automations involving REST APIs, data stores, transformation logic, LLM integrations and workflow orchestration.

03

Integrate Large Language Models

Implement prompt engineering, structured output parsing and validation against defined quality and acceptance thresholds.

04

Build Quality Into AI Automations

Create tests covering core logic, external dependencies and LLM output quality to ensure reliable production behavior.

05

Deploy and Stabilize Solutions

Deploy solutions into production, monitor initial runs and manage hypercare until the automation reaches stable operation.

06

Build Reusable Engineering Patterns

Contribute reusable components and patterns to the shared automation library across multiple projects.

07

Develop Full-Stack Automation Tools

Build lightweight React and FastAPI interfaces for review queues, exception dashboards, approvals and configuration.

08

Develop Agentic Workflows

Contribute to multi-step AI workflows involving tool use, memory, planning and evaluation frameworks.

09

Support Agile Delivery

Participate in sprint planning, standups, reviews and retrospectives while identifying blockers early.

10

Enable Operations Teams

Hand over completed automations with documentation that non-engineering users can understand and follow.

Build Reliable LLM-Powered Automations

Prompt Engineering

Design prompts that produce predictable, useful and structured outputs for business workflows.

Structured Outputs

Parse and validate LLM responses against predefined schemas and business requirements.

Output Validation

Treat hallucination and unreliable AI output as engineering problems requiring explicit quality controls.

AI Quality Mindset

The role goes beyond simply calling an LLM API. Production AI automation requires validation, error handling, acceptance criteria, monitoring and clear human escalation paths.

Connect Systems Reliably

REST APIs

Build reliable API integrations with authentication, pagination, rate limiting, retries and error handling.

Integration Debugging

Diagnose integration failures and understand system behavior even when documentation is incomplete.

Data Integration

Connect automation workflows with relational databases, cloud storage and enterprise data platforms.

REST APIs Authentication Rate Limiting Pagination Error Handling API Integration

Work With Enterprise Data Stores

The engineer should be comfortable navigating data structures, querying data and integrating enterprise data stores into automation workflows.

PostgreSQL Snowflake S3 Blob Storage SQL Data Transformation Cloud Data Stores

Build the Next Generation of Intelligent Workflows

As the programme's agentic automation capabilities mature, the role contributes to workflows where AI can reason, use tools, maintain context and execute multi-step tasks.

AI Agents Agentic Workflows Tool Use Memory Planning Orchestration LLM Evaluation Human-in-the-Loop Output Validation

Build Interfaces When Automation Needs Human Interaction

React

Create lightweight frontends for human review queues, approval workflows and automation configuration.

FastAPI

Build lightweight backend services and APIs that expose automation capabilities to human-facing applications.

Operational Dashboards

Create exception and monitoring interfaces that allow teams to review automation outcomes and intervene when required.

Production-Grade Development

Python Development 6+ years of production Python development experience building systems that operate reliably beyond local environments.
Git & Code Review Strong Git practices including branching, pull requests, meaningful commits and constructive code reviews.
Testing Ability to test core logic, external integrations and LLM output quality against acceptance criteria.
Agile Delivery Familiarity with Scrum, Kanban, Jira and sprint-based engineering delivery.
Production Monitoring Ability to monitor initial deployments, identify failures and stabilize automation through hypercare.
Technical Communication Ability to explain what an automation does, its limitations and its failure behavior to non-technical stakeholders.

Ask the Right Questions Before Building

Strong candidates do more than implement requirements. They examine process specifications critically, identify hidden assumptions and determine where an automation is most likely to fail.

01

Find Missing Information

Identify undocumented process steps, dependencies and assumptions before implementation begins.

02

Identify Failure Points

Anticipate where integrations, data, LLM outputs or business processes are most likely to break.

03

Design for Recovery

Build error handling, validation and human-in-the-loop mechanisms into the automation architecture.

04

Own the Outcome

Focus on whether the automation actually works for the business, not simply whether the code runs.

What You Should Bring

6+ Years Python Strong production experience developing Python-based systems and automation.
Production LLM Experience Direct experience integrating Large Language Models into production workflows.
REST API Expertise Experience with authentication, pagination, rate limiting, error handling and integration troubleshooting.
Data Store Knowledge Working knowledge of PostgreSQL, Snowflake, S3/Blob storage and SQL.
AI Automation Experience with prompt engineering, structured outputs, validation and hallucination-aware engineering.
Agile Engineering Familiarity with Scrum, Kanban, Jira and collaborative software delivery practices.

Skills & Technologies

Python Generative AI LLMs Prompt Engineering AI Automation Agentic AI REST APIs SQL PostgreSQL Snowflake S3 Blob Storage FastAPI React Git Jira LLM Evaluation Human-in-the-Loop Workflow Orchestration

Remote Opportunity

This position can be located remotely with Bangalore or Pune as the specified location base.

Remote Bangalore Pune Global Operations AI & Automation

Build Production AI Automation

Turn complex business processes into reliable, scalable automations powered by Python, APIs, data and Generative AI.

Apply Now ↗