About Pelico

We are creating the factory of the future where disruptions are avoided, processes synchronized and value captured. Our factory operations management platform enables factory teams to be more agile and resilient in a world where supply chain disruptions occur every 16 minutes. Pelico empowers users to identify bottlenecks, avoid problems, and focus on innovation instead of fire-fighting. Since our foundation in 2019, we’ve partnered with industry leaders across aerospace, industrial equipment, and luxury watchmaking, revolutionizing factory operations in over 15 countries. Esteemed clients include Airbus, Safran, Cartier, Daikin, and Eaton.

Our Team

With a dynamic team of over 180 professionals across the US and France, Pelico is a melting pot of top-tier talent from Tech, Data Science, and Manufacturing domains.
Our collaborative environment fosters innovation and excellence, driving us to solve complex challenges and shape the future of manufacturing.

Our work has been recognized by Safran (Digital Transformation Award) and Microsoft (scale-up of the year).

Engineering turns Product ambition into scalable, reliable solutions that empower on-site operational teams.

We design a platform that handles high volumes, concurrent users, and complex workflows, while remaining modular, maintainable, and future-proof.

Your Role’s Mission

You will join Pelico’s AI team to build and scale our agentic AI framework and MCP ecosystem, powering intelligent assistants and automation within the platform.

Your work will help deliver production-grade AI agents used daily by industrial teams, while supporting strategic AI initiatives with leading manufacturers.

In this role, you will design and implement the infrastructure, services, and developer tooling required to build secure, scalable, and reliable AI systems integrated with Pelico’s platform.

What You Will Do

1. Build Pelico’s agentic AI framework

Design and implement the core components of Pelico’s agentic AI framework

Develop services that allow AI agents to interact safely with Pelico’s operational systems

Implement robust mechanisms for tool usage, orchestration, and context management

Ensure that the framework supports production-grade reliability and scalability

2. Develop and maintain MCP-based integrations

Build and maintain MCP servers and integrations enabling AI agents to access Pelico platform capabilities

Implement service-level contract validation and automated testing to ensure non-regression as MCP ownership decentralizes across teams

Improve tooling and standards to make MCP integrations safe, maintainable, and easy to evolve

3. Enable scalable deployment of AI services

Design deployment workflows that allow AI services and MCP servers to be deployed reliably across different platform versions

Reduce operational friction by automating backporting, schema alignment, and compatibility layers

Improve the overall developer experience for deploying and maintaining AI services

4. Support strategic AI POCs with key customers

Work closely with product and AI teams to support customer-facing AI initiatives

Help deliver AI-powered capabilities for our clients.

Translate experimental AI capabilities into production-ready systems

Your Impact

Your work will directly shape Pelico’s AI platform and agentic capabilities, enabling us to deliver intelligent assistants that support complex operational workflows in factories.

By building a scalable AI infrastructure and reliable MCP ecosystem, you will help ensure Pelico can move from experimental AI features to production systems used daily by industrial teams worldwide.

What We’re Looking For

Core Engineering Background

• 2–5 years of experience as a Software Engineer, ideally with exposure to AI-enabled systems

• Strong computer science fundamentals (data structures, algorithms, system design)

• Proven track record of building production-grade applications with a focus on reliability, maintainability, and scalability

AI & LLM Experience

• Experience working with LLM-based applications or modern AI tooling (RAG pipelines, embeddings, vector databases, prompt engineering)

• Hands-on experience integrating LLM APIs and frameworks (Pedantic AI, LangChain, Google ADK or similar)

• Ability to turn AI experiments into production-ready systems

Mindset & Ways of Working

• Strong curiosity and experimentation mindset; interest in exploring new AI capabilities and building side projects with LLM technologies

• High level of ownership and ability to operate in fast-moving environments

• We are a team of +40 nationalities, Professional proficiency in English is mandatory