Expert, AI Engineering

We are looking for an Applied LLM Engineer to design, fine-tune, and integrate large language models into practical internal applications such as AI assistants, knowledge systems, and workflow automation tools.

You will play a key role in leveraging LLMs to build different AI Agents to enhance employee productivity, simplify information retrieval, and enable intelligent task automation.

Job's Responsibilities

Design and Architect LLM-Powered Internal Productivity Tools- Design the overall system architecture for complex LLM applications, ensuring scalability, security, and seamless integration with existing data sources and internal APIs.

- Prototype and validate LLM applications through iterative testing with internal user groups.

- Select appropriate models & frameworks and create implementation roadmaps for LLM initiatives.

- Ensure solutions adhere to security, privacy, and compliance standards for internal data.

Develop and Optimize RAG Systems for Enterprise Knowledge Management- Build end-to-end Retrieval-Augmented Generation (RAG) pipelines, from document ingestion and chunking to vector indexing (e.g.

using FAISS, Milvus, or tools from cloud providers etc.) and intelligent retrieval with re-ranking.

- Design and optimize retrieval strategies, including hybrid search and re-ranking mechanisms.

- Continuously experiment with and implement advanced techniques to improve retrieval accuracy, answer relevance, and system latency.
- Own the health and evolution of internal knowledge bases, ensuring information is accurate, up-to-date, and accessible

Build and Maintain AI Agents for Workflow Automation

- Develop multi-step AI agents capable of executing tasks such as data entry, document generation, and system monitoring.
- Implement function calling and tool-use capabilities to integrate agents with internal software and APIs.
- Create orchestration workflows using frameworks like LangChain or LangGraph to manage agent execution.
- Monitor agent performance, log interactions, and implement fallback mechanisms for error handling.
- Iterate on agent design based on usability testing and operational feedback.

Own the Deployment and MLOps Lifecycle for LLM Applications- Build and maintain CI (Continuous Integration) /CD (Continuous Delivery) pipelines for automated testing, deployment, and rollback of LLM services using frameworks like FastAPI or Flask.

- Utilize cloud AI platforms (e.g., Azure AI, AWS Bedrock, Alibaba Bailian) or containerization (Docker, Kubernetes) to deploy and scale applications.

- Establish monitoring for application health, performance metrics, AI-specific concerns (e.g., hallucination rates, token usage), and operational costs.

Qualifications and Experience

1.

Bachelor's degree or above in Computer Science, Artificial Intelligence, Electrical Engineering or a related field.

2.

5+ years of software engineering experience, with at least 2 years focused on building and deploying production applications using...