Flexing It®
Website:
flexingit.com
Job details:
Our client, a leading global specialist in energy management and automation is looking for an Consultant - 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
Key Responsibilties;
1. Design & Architect LLM-Powered Internal Tools;
- Design scalable, secure architectures for LLM-based internal applications such as AI assistants, knowledge systems, and automation tools.
- Prototype, validate, and iterate on LLM solutions through testing with internal stakeholders.
- Select appropriate models, frameworks, and tools; define clear implementation roadmaps.
- Ensure compliance with data security, privacy, and internal governance standards.
2. Develop & Optimize Enterprise RAG Systems;
- Build end-to-end Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embedding, vector indexing, and retrieval.
- Implement and optimize hybrid search, re-ranking, and retrieval strategies to improve accuracy and relevance.
- Continuously experiment with techniques to reduce latency and improve response quality.
- Own and maintain internal knowledge bases, ensuring data accuracy and freshness.
3. Build & Maintain AI Agents for Workflow Automation
- Develop multi-step AI agents to automate tasks such as document generation, data processing, and system monitoring.
- Implement tool use and function calling to integrate agents with internal systems and APIs.
- Design and orchestrate agent workflows using frameworks such as LangChain or LangGraph.
- Monitor agent behavior, implement logging and fallback mechanisms, and iterate based on user feedback.
4. Own Deployment & MLOps for LLM Applications
- Build and maintain CI/CD pipelines for testing, deployment, rollback, and versioning of LLM services.
- Deploy and scale applications using cloud AI platforms or containerized environments (Docker, Kubernetes).
- Monitor system health, performance, hallucination rates, token usage, and operational costs.
- Continuously improve reliability, scalability, and cost efficiency of LLM solutions.
NOTE;
Duration- 12 months (extendable)
Location- Bangalore Avinya campus (Hybrid)
Capacity- Full time
Click on Apply to know more.