Overview
Design, build and deploy production-grade Generative AI systems, including LLM-powered applications and agentic frameworks, that enhance operational intelligence and automate complex workflows across container terminals globally.
What you'll do
- Design, implement and deploy production-grade Generative AI solutions that enhance operational intelligence and automation across terminal workflows.
- Develop LLM-powered systems including retrieval-based reasoning, AI copilots and task-oriented AI agents that support decision-making in complex operational environments.
- Design robust data pipelines that enable reliable context retrieval, semantic understanding and grounded response generation.
- Build and maintain end-to-end GenAI solution lifecycles, from data preparation and experimentation through deployment, monitoring and iteration.
- Implement structured evaluation frameworks to measure output quality, reliability, latency, cost efficiency and hallucination risk.
- Enhance system robustness through prompt design, tool integration, validation layers and guardrail mechanisms.
- Contribute to production readiness through testing, observability and performance optimization practices.
- Work closely with stakeholders to translate operational challenges into structured AI problem statements with measurable success criteria.
- Communicate model behaviour, limitations and trade-offs clearly to technical and non-technical audiences.
- Own delivery of solutions within defined architectural patterns and engineering standards.
What you'll need
- 5+ years of industry experience building and deploying production-grade AI/ML systems, with strong hands-on experience in Generative AI systems.
- PhD or M.Sc. in Machine Learning, Computer Science, Applied Mathematics, Statistics, Engineering or related quantitative discipline, or equivalent practical experience.
- Practical experience with Large Language Models (LLMs) and Transformer architectures.
- Practical experience with Retrieval-Augmented Generation (RAG) systems.
- Practical experience with embedding-based semantic search.
- Practical experience with prompt engineering and structured reasoning workflows.
- Practical experience with AI agents or tool-integrated LLM systems.
- Ability to evaluate model outputs for reliability, faithfulness, performance and cost efficiency in real-world environments.
- Deep proficiency in Python and standard software engineering practices, including Object-Oriented Programming, design patterns, unit testing and validation, version control, and maintainable and scalable system design.
- Experience working with cloud environments, CI/CD pipelines, containerization (Docker) and monitoring and performance tracking.
- Comfort delivering solutions in fast-paced, agile environments.
Nice to have
- Experience with vector databases and semantic indexing platforms.
- Exposure to AI observability and governance practices.
- Domain experience in logistics, scheduling or operational optimization environments.
- Experience integrating GenAI systems with optimization or simulation models.
Details
- Location: Bengaluru, India.
Read the full description and apply on the company’s own careers page.