Job Description

About the Role: As an AI Engineer, you will play a critical role in leveraging data science to drive significant business impact. You will lead the development of Agentic AI applications and traditional ML models, building intelligent systems that can reason through complex scenarios while also providing predictive and prescriptive insights.

You will be responsible for architecting solutions that are not only intelligent but safe, observable, and robust. You will bridge the gap between modern Large Language Models (LLMs) and traditional statistical techniques, ensuring that AI agents operate within strict guardrails and are backed by rigorous data analysis

Job Responsibilities:

• Design and build state-of-the-art AI agents using modern orchestration frameworks (e.g., LangGraph, LangChain, Google ADK) to automate complex reasoning tasks.
• Design and implement supervised and unsupervised machine learning models (e.g., regression, classification, clustering) and statistical experiments to support data-driven decision-making.
• Develop advanced RAG (Retrieval-Augmented Generation) pipelines and API connectors to ingest and synthesize data from diverse sources, including internal databases, unstructured technical documents, and external third-party data.
• Implement robust safety layers and input/output validation using specialized frameworks to prevent hallucinations, ensure data privacy, and maintain compliance.
• Build comprehensive monitoring pipelines using advanced evaluation tools (e.g., Arize Phoenix, Langfuse) to trace agent reasoning steps, track token usage, and monitor latency in production.
• Adopt rigorous evaluation frameworks (e.g., Ragas, GenAI Evaluation Service) to measure performance. Stay updated on research papers and cutting-edge algorithms in both the GenAI and ML domains.
• Develop and deploy AI solutions exclusively within the Cloud Platform (GCP/AWS/Azure) ecosystem, utilizing Vertex AI, Cloud Run, and BigQuery.

Qualifications:

• 3+ years of professional experience in Data Science or Software Engineering, with a strong dual focus on Generative AI/LLM applications and traditional Machine Learning.
• Bachelor’s or Master’s degree in a quantitative field (e.g., Computer Science, AI, Statistics, Mathematics, or Engineering). A PhD is preferred.
• 2+ years of hands-on experience with supervised/unsupervised learning and statistical modeling.
• Proven experience building Agentic workflows (reasoning loops, tool use/function calling) rather than simple chatbots.
• Deep understanding of the GCP stack for AI/Data (Vertex AI, BigQuery).

Technical Skills:

• Expert proficiency in Python for building autonomous agents and model interaction (e.g., LangGraph, LangChain, Google ADK).
• Advanced proficiency in Python libraries such as Scikit-learn, NumPy, Pandas, Matplotlib, TensorFlow, or PyTorch.
• Skilled in integrating diverse data sources via SQL, Vector Databases, and APIs. Experience with data augmentation and efficient loading techniques.
• Proficiency in observability frameworks, guardrail implementation, and the Model Context Protocol (MCP).
• Deep experience with GCP services, specifically Vertex AI, Cloud Run, and BigQuery for deploying scalable AI solutions.

Functional Skills:

• Ability to decompose complex business challenges into executable AI agent workflows and technical specifications.
• Excellent verbal and written communication skills, with a demonstrated ability to translate complex technical information into simple, understandable language for non-technical audiences.
• Strong skills in building relationships and collaborating effectively with stakeholders to contribute to data-driven decision-making.