AI Engineer

The Agentic AI Engineer will be responsible for developing, optimizing, and deploying AI-powered autonomous agents on GCP. This role involves fine-tuning LLMs, designing AI workflows, integrating APIs, and building scalable AI applications using GCPs AI/ML tools.
Key Responsibilities:
Develop agentic AI solutions using LangChain, AutoGen, CrewAI, and OpenAI APIs on GCP.
Fine-tune LLMs (PaLM 2, Gemini, GPT) on Vertex AI for enterprise-specific applications.
Implement multi-agent collaboration frameworks for intelligent automation and orchestration.
Optimize vector search, embeddings, and retrieval mechanisms using Vertex AI Matching Engine and FAISS.
Integrate AI agents with APIs, microservices, and event-driven architectures using Cloud Functions and Cloud Run.
Design and implement data pipelines for AI workflows using BigQuery, Dataflow, and Cloud Composer.
Work with Vertex AI Pipelines to manage ML model training, deployment, and continuous monitoring.
Develop real-time AI applications leveraging Pub/Sub, Dataflow, and Cloud AI services.
Implement observability, logging, and monitoring mechanisms for AI models in production.
Collaborate with AI architects, ML engineers, and data scientists to optimize AI model performance.
Required Skills & Experience:
7+ years in AI/ML development, software engineering, or data science.
Strong experience with Python, LangChain, AutoGen, CrewAI, OpenAI API, and GCP AI tools.
Expertise in LLMs, prompt engineering, RAG, embeddings, and hybrid search techniques.
Hands-on experience with vector databases (Vertex AI Matching Engine, Pinecone, Weaviate, ChromaDB).
Experience with Google Cloud Functions, Cloud Run, and Pub/Sub for event-driven AI applications.
Familiarity with workflow orchestration tools like Cloud Composer (Airflow).
Strong understanding of Google Cloud IAM, security best practices, and AI governance.
Experience deploying AI models on GPUs/TPUs using GCP AI infrastructure.
Preferred Qualifications:
Experience with MLOps & LLMOps using Vertex AI Pipelines and Model Monitoring.
Hands-on experience fine-tuning LLMs on domain-specific datasets.
Knowledge of ethical AI, bias detection, and model interpretability.
Contributions to open-source AI/ML projects or research papers.