About the Role
FaresPlanet is looking for an AI Engineer to build and productionize intelligent software systems that solve real business and customer problems. This role sits at the intersection of software engineering, AI engineering, platform engineering, and product delivery. You will work on practical AI applications involving Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), prompt engineering, agent frameworks, tool calling, APIs, databases, and event-driven systems. You will be expected to take solutions from ambiguous requirements through implementation, testing, deployment, monitoring, and continuous improvement.
Key Responsibilities
- Design, develop, test, and deploy production-grade AI-powered applications and services.
- Build LLM-based workflows using RAG, prompt engineering, agent frameworks, structured outputs, and tool/function calling.
- Integrate AI capabilities with existing products, APIs, databases, internal systems, and third-party services.
- Design reliable AI application architectures with appropriate controls for latency, cost, security, reliability, and scalability.
- Develop evaluation strategies for AI systems, including quality checks, test datasets, regression testing, and monitoring of production behavior.
- Work with product, engineering, business, and customer-facing stakeholders to translate ambiguous requirements into practical technical solutions.
- Prototype rapidly, validate approaches with real users or business stakeholders, and convert successful prototypes into maintainable production systems.
- Build automation and developer workflows that improve the speed and reliability of AI application delivery.
- Investigate production issues involving application logic, APIs, data pipelines, model behavior, infrastructure, latency, and reliability.
- Contribute to engineering standards, documentation, observability, CI/CD, testing, and operational practices for AI systems.
Required Qualifications
- At least 2 years of professional experience in software engineering, AI engineering, platform engineering, DevOps, or enterprise application development; candidates with 2–4 years of relevant experience are targeted for this position.
- Strong programming experience in Python, Java, JavaScript, or TypeScript.
- Hands-on experience with LLMs, RAG, prompt engineering, agent frameworks, and tool/function calling.
- Experience integrating applications using APIs, databases, and event-driven systems. Page 1 FaresPlanet | AI Engineer Understanding of cloud platforms, CI/CD, observability, monitoring, logging, and production support.
- Strong problem-solving, stakeholder-management, collaboration, and communication skills.
- Ability to take solutions from ambiguous requirements through production deployment.
- Strong software engineering fundamentals, including version control, testing, debugging, API design, and maintainable code.
Technical Skills & Competencies
Programming Generative AI Integration Python, Java, JavaScript, TypeScript, or equivalent production programming experience. LLMs, prompt design, RAG pipelines, embeddings, vector search, agent frameworks, tool calling, structured outputs, and AI application patterns. Git, code review, automated tests, documentation, secure development practices, and pragmatic system design. REST APIs, authentication, databases, queues/events, webhooks, third-party integrations, and service-to-service communication. Cloud & Platform Production Engineering Engineering Quality Familiarity with AWS, Azure, GCP, containers, CI/CD pipelines, deployment automation, and environment management. Logging, metrics, tracing, alerting, incident response, performance analysis, reliability, and production troubleshooting.
Pay: ₹2,500,000.00 - ₹3,000,000.00 per year
Benefits:
Ability to commute/relocate:
- Mohali, Punjab: Reliably commute or planning to relocate before starting work (Required)
Application Question(s):
- “How many years of hands-on AI/GenAI engineering experience do you have? Briefly describe the most complex AI application you have built and deployed to production, including the LLM/model, RAG/agent architecture, technologies used, and your personal contribution.”
Experience:
- AI Engineer: 4 years (Required)
Language:
- Fluent English (Required)
Work Location: In person
