Apply For This Job
* Required
Junior AI Engineer
Work on production AI backend services — building shared tooling, integrating LLM providers, and improving reliability across our Python microservices on AWS.
Your Salary
Based on Experience
Job Type
On-site
Location
Mohali, Punjab
Position
Junior AI Engineer
Employment type
Full-time
Our Responsibility
- • Build an internal Python library that unifies common patterns (LLM clients, database wrappers, observability, alerting) used across services.
- • Integrate LiteLLM for multi-provider fallbacks, retries, and cost tracking so AI calls degrade gracefully instead of failing hard.
- • Improve and build CI/CD pipelines, write tests for critical paths, and automate repetitive operational tasks.
- • Contribute across the service suite as needed — bug fixes, new endpoints, and performance improvements.
What You Will Do
- • Design and build shared Python tooling for LLM clients, database wrappers, observability, and alerting.
- • Integrate LiteLLM for multi-provider fallbacks, retries, and cost tracking across AI services.
- • Write tests for critical paths using pytest and maintain high test coverage.
- • Automate repetitive operational tasks and improve CI/CD pipelines.
- • Build and consume REST APIs using FastAPI.
- • Work with MongoDB and/or PostgreSQL for data persistence.
- • Deploy and manage services using Docker on AWS infrastructure.
- • Collaborate with the AI Lead on architecture decisions and production reliability.
Skills needed for Success
- • 6 months to 1.5 years of relevant experience.
- • Solid Python skills — async/await, type hints, standard library.
- • Experience building or consuming REST APIs (FastAPI, Flask, or Django).
- • Exposure to at least one LLM provider API (OpenAI, Gemini, Mistral, etc.).
- • Comfort navigating and contributing to an existing codebase.
- • Git workflow proficiency — branches, PRs, code reviews.
- • Experience with MongoDB or PostgreSQL.
- • Familiarity with Docker and AWS.
- • Experience with pytest or any testing framework.
- • Experience with LiteLLM, LangChain, or similar LLM orchestration tools.
- • Proficiency with AI coding tools (Cursor, Copilot, Claude).
What We Offer
- • Work directly on production AI services powering real compliance decisions.
- • Hands-on experience with multi-provider LLM infrastructure (OpenAI, Gemini, Mistral).
- • Build internal tooling used across the entire AI engineering team.
- • Exposure to modern Python microservice architecture on AWS.
- • Collaborative, fast-moving team with high ownership and direct impact.
- • Competitive compensation based on experience.
Our culture
Transparency And Open communication
Collaborate Over competition