• Design and implement scalable agentic frameworks that coordinate multiple AI agents to deliver accurate and reliable outcomes. • Build and optimize natural language query solutions that provide compliant, intuitive, and self-service access to enterprise data. • Develop and maintain evaluation frameworks for LLMs and prompts, driving measurable improvements in accuracy, scalability, and resilience. • Partner with data engineering peers to integrate AI orchestration with Python, SQL, and Snowflake pipelines. • Contribute to AI-powered summarization and explanation tools that enhance reporting, insights, and executive reviews. • Collaborate cross-functionally with product, analytics, and business teams to ensure solutions meet measurable business goals.

• Design, develop and evolve agents and workflows using MCP-based architectures • Build RAG pipelines and context-retrieval mechanisms using vector databases • Integrate agents with APIs, tools and external services to execute complex flows • Develop agents in Python using Google ADK • Build and maintain agentic flows with LangChain and LangGraph • Integrate AI models and services via Vertex AI and Gemini models • Implement build, test and deployment pipelines for agents and workflows • Define architectural standards, reusable components and technical governance guidelines for the platform • Ensure solution observability through logs, metrics and tracing • Collaborate with technical teams to ensure consistent integration between AI agents and enterprise applications • Design solutions aligned with business processes, integrations and objectives • Ensure developed components are scalable, reusable and prepared for continuous evolution

Role Description This is a remote position. Design, build, and deploy production-ready AI applications—including RAG-powered solutions, conversational AI, and document intelligence—on Azure/AWS/GCP. Collaborate with architects, data engineers, and domain SMEs to deliver outcomes in areas like FNOL, claims automation, underwriting, and agent assist. Key Responsibilities - Design and implement end-to-end AI/ML solutions from data prep to production deployment. - Build RAG pipelines with robust retrieval, re-ranking, grounding, and evaluation. - Develop AI applications such as conversational agents and document intelligence workflows (extraction, classification, validation). - Implement image/document processing (OCR, layout analysis, table extraction, redaction). - Integrate with enterprise systems and APIs; enable tool use/function calling where applicable. - Optimize for latency, accuracy, cost, and safety. - Package and deploy with Docker/Kubernetes/Serverless; automate with CI/CD. - Write clean, testable code; contribute to internal accelerators, templates, and best practices. Qualifications - 10+ years of hands-on experience delivering AI/ML software to production. - Strong in Python and one of PyTorch / TensorFlow. - Solid understanding of LLMs, prompting, function calling/tools, evaluation, and vector search. - Experience with RAG (indexing, chunking, embeddings, retrieval, re-rankers, grounding). - Practical exposure to Document AI and Conversational AI in real-world workflows. - Cloud experience on Azure, AWS, or GCP. - Experience in insurance (FNOL, claims adjudication, underwriting, billing, policy servicing, agent portals, etc.) will be preferred. Benefits - Diversity Inclusion: At Exavalu, we are committed to building a diverse and inclusive workforce. We welcome applications for employment from all qualified candidates, regardless of race, color, gender, national or ethnic origin, age, disability, religion, sexual orientation, gender identity or any other status protected by applicable law. - We nurture a culture that embraces all individuals and promotes diverse perspectives, where you can make an impact and grow your career. - Exavalu also promotes flexibility depending on the needs of employees, customers, and the business. It might be part-time work, working outside normal 9-5 business hours, or working remotely. - We also have a welcome back program to help people get back to the mainstream after a long break due to health or family reasons.

• You'll design and maintain the infrastructure that powers client deliverables - ingestion pipelines, data models, transformation layers, and the orchestration that keeps it all running. • You'll build and ship AI applications - not prototype them. That means writing production-grade code, designing agent workflows, and integrating LLMs into systems where accuracy and reliability actually matter. • You'll architect agent systems with clear evaluation criteria, human-in-the-loop checkpoints where they matter, and monitoring that tells you when something goes wrong. • You'll own deployment end-to-end - containerized services, Kubernetes orchestration, cloud infrastructure, and the CI/CD pipelines that keep everything moving. • As a founding engineer, you'll help identify what we build repeatedly across engagements and turn it into durable internal infrastructure - shared data models, evaluation frameworks, deployment patterns.