AI/ML Engineer

Job Description:

· This role is critical for designing, developing, and optimizing the core AI and RAG components of the system.

Key Skills & Responsibilities

· Gen AI:Deep understanding of generative AI models, LLMs, and their application in conversational interfaces. Experience with fine-tuning or adapting models for specific tasks.

· LangGraph:Expertise in building agentic systems and state machines using LangGraph. Understanding of agent orchestration, managing conversational flow, and integrating various tools/models.

· Python:Strong proficiency in Python, including experience with relevant AI/ML libraries (e.g., TensorFlow, PyTorch, scikit-learn, Hugging Face).

· RAG Implementation:Experience in designing and implementing Retrieval Augmented Generation systems, including vector databases, embedding techniques, and efficient retrieval strategies.

· Cloud Platform (Google Cloud):Experience deploying and managing AI/ML workloads on Google Cloud Platform (GCP) has added advantage. Familiarity with relevant services like Vertex AI, Cloud Functions, Cloud Run, or GKE for model deployment.

· Async Programming:Have understanding or ability to write efficient asynchronous code for handling potentially long-running AI model calls and external API interactions.

· REST:Understanding of RESTful principles for integrating AI services with other parts of the system.

· Logging:Experience with implementing robust logging for monitoring AI model performance, identifying issues, and tracking usage. Familiarity with tools like Splunk is a plus