AI/ML Engineer/Specialist - LLM

What Youll Do :

- Design, develop and deploy agent-based AI systems using LLMs.

- Build and scale Retrieval-Augmented Generation pipelines for real-time and offline inference.

- Develop and optimize training workflows for fine-tuning and adapting models to domain-specific tasks.

- Collaborate with cross-functional teams to integrate knowledge base into agent frameworks.

- Drive best practices in AI Engineering, model lifecycle management, and production deployment on Google Cloud (GCP).

- Implement version control strategies using Git, manage code repositories and ensure best practices in code management.

- Develop, manage CI/CD pipelines using Jenkins or other relevant tools to streamline deployment and updates.

- Monitor, evaluate, and improve model performance postdeployment on Google Cloud.

- Communicate technical findings and insights to non-technical stakeholders.

- Participate in technical discussions and contribute to strategic planning.

What Experience You Need :

- 7+ years of experience in AI/ML engineering, with a strong focus on LLM-based applications.

- At least 10+ years of experience in IT overall.

- Proven experience in building agent-based applications using Gemini, OpenAI or similar models.

- Deep understanding of RAG systems, vector databases, and knowledge retrieval strategies.

- Hands-on experience with LangChain and LangGraph frameworks.

- Solid background in model training, fine-tuning, evaluation and deployment.

- Strong coding skills in Python and experience with modern MLOps practices.

What Could Set You Apart :

- Experience with Google Cloud services like BigQuery, Vertex AI, Agent Builder, ADK.

- Exposure to Angular framework.