About the Role
We are looking for a Staff ML Engineer to build and optimize AI-driven data extraction and standardization systems. As we scale, ensuring our AI agents can reliably extract, structure, and standardize data across diverse sources is critical. This role will focus on developing a multi-agent AI system where specialized agents work together to:
- Extract & Standardize Data from structured and unstructured sources with high accuracy.
- Optimize Multi-Agent Interactions to improve extraction workflows and minimize inconsistencies.
- Enhance Performance & Scalability through fine-tuning, prompt optimization, and intelligent workflow design.
- Implement MLOps Best Practices for monitoring, deployment, and continuous improvement of AI models.
This is an in-office role, where you will collaborate closely with ML researchers, data engineers, and product teams to build robust AI-powered solutions.
Responsibilities
- Design & Optimize a Multi-Agent AI System for structured data extraction and standardization using A2A and MCP.
- Fine-Tune LLMs & Optimize Prompts to enhance extraction accuracy and contextual understanding.
- Develop Intelligent Workflows that improve agent coordination, response quality, and feedback loops.
- Implement Performance Optimization Strategies to improve latency, accuracy, and cost-efficiency.
- Automate AI Model Evaluation using response quality metrics and continuous learning techniques.
- Deploy & Monitor AI Models with MLOps tools for logging, monitoring, and automated retraining.
- Ensure Model Reliability & Explainability by implementing robust monitoring and debugging workflows.
- Work Closely with Data & Engineering Teams to ensure seamless integration into business workflows.
Requirements
- 5+ years of experience in machine learning, deep learning, or AI engineering.
- Strong expertise in LLM fine-tuning, prompt engineering, retrieval-augmented generation (RAG), Model Context Protocol (MCP), and agent2agent (A2A).
- Experience with multi-agent AI architectures, model optimization, and distributed AI systems.
- Proficiency in Python, TensorFlow, PyTorch, and Hugging Face.
- Hands-on experience with LLM evaluation, response ranking, and feedback-driven model improvements.
- Familiarity with Google Cloud AI tools, BigQuery, and scalable ML infrastructure.
- Strong understanding of data extraction, entity recognition, schema mapping, and data validation techniques.
- Experience in orchestrating ML workflows using tools like Ray, Airflow, or LangGraph.
- MLOps Experience: Expertise in monitoring, logging, and automating ML model deployment with tools like MLflow, Kubeflow, Vertex AI, or SageMaker.
- Understanding of vector databases and efficient retrieval mechanisms.
Nice to Have
- Experience with real-time AI inference and event-driven architectures.
- Exposure to LLMOps, MLOps, and ML architectures supporting AI/ML workflows.
- Proficiency with Node and Typescript.
What We Offer
- Competitive salary & benefits.
- Collaborative in-office work environment.
- Opportunity to work with cutting-edge AI and ML technologies.
- Exciting challenges & rapid growth opportunities.
- Continuous learning & professional development.
If you're passionate about building scalable AI systems, optimizing LLM performance, and integrating MLOps best practices, we'd love to hear from you. Apply now.