• Design, build, and scale production-ready Multi-Agent Systems (MAS) and complex AI workflows. • Bridge the gap between simple LLM prompting and robust, deterministic, enterprise-scale software engineering. • Leverage ADK to orchestrate specialized micro-agents, build reliable graph-based workflows, and integrate AI agents with enterprise datastores, APIs, and Model Context Protocol (MCP) tools. • Move AI from conceptual prototypes to high-throughput, mission-critical business systems deployed on Agent Engine.

• Lead the technical architecture and implementation of an edge-native intelligent processing platform supporting distributed sensing, edge inference, and resilient mission operations. • Design scalable software architectures supporting heterogeneous edge computing devices, software-defined radios, embedded compute platforms, and cloud-enabled mission services. • Develop high-performance backend services using Python, FastAPI, asynchronous programming, and modern distributed software engineering techniques. • Lead integration of Software Defined Radio (SDR) platforms (such as Ettus USRP, GNU Radio, or equivalent SDR ecosystems) into software pipelines for real-time data processing and analytics. • Design resilient distributed processing frameworks capable of operating under degraded, disconnected, intermittent, and bandwidth-constrained communications. • Develop intelligent data processing pipelines that reduce communication overhead through feature extraction, prioritization, and adaptive data management. • Design peer-to-peer communication services supporting decentralized collaboration across heterogeneous edge devices. • Implement secure synchronization, workload distribution, and fault-tolerant processing across multiple edge computing nodes. • Lead software integration across embedded Linux systems, containerized services, edge compute devices, and cloud infrastructure. • Establish software architecture standards, CI/CD pipelines, testing frameworks, DevSecOps practices, and engineering best practices. • Collaborate closely with AI engineers to integrate machine learning inference capabilities into production software. • Produce technical documentation, software architecture artifacts, interface specifications, and engineering design documentation. • Support technical demonstrations, customer engagements, and prototype evaluations. • Mentor junior engineers while maintaining significant hands-on software development responsibilities.

• Contribute to the design and evolution of Expression's Agentic AI platform by defining scalable architectures for enterprise AI applications and services, including system architecture, core platform components, tooling, automation, coding standards, and platform performance, scalability, and reliability. • Architect, deliver, and optimize production-grade LLM services, agent workflows, orchestration layers, retrieval pipelines, and vector search technologies. • Provide technical leadership and mentorship: guide architecture and design reviews, grow engineers, and raise the bar for engineering quality and technical decision-making across the team. • Develop high-performance Python APIs and scalable backend services using FastAPI, asynchronous programming techniques, and modern software engineering practices. Set the technical direction and engineering standards for high-performance, scalable backend services and APIs, and champion modern software engineering best practices across the team. • Build and maintain the underlying AI platform that supports secure, observable, resilient, and production-ready AI workloads. • Design and implement AI governance capabilities, including guardrails, policy enforcement, model lifecycle management, responsible AI practices, and compliance with federal security and governance requirements. • Develop automated testing and evaluation strategies for AI-enabled applications, including prompt evaluation, model evaluation, regression testing, integration testing, and quality assurance. • Implement LLM observability, monitoring, logging, telemetry, performance metrics, and resilience strategies to ensure reliable production operation. • Design, implement, and maintain CI/CD pipelines and deployment automationDefine and drive CI/CD and deployment automation strategy to support secure, efficient delivery of AI services. • Collaborate with Product, UX, Infrastructure, Security, and other cross-functional teams to continuously improve platform capabilities and deliver customer-focused solutions. • Collaborate with clients, lead product demonstrations, and communicate technical concepts and platform capabilities to both technical and executive audiences. • Produce clear technical documentation, architecture diagrams, design proposals, and other engineering artifacts.

• Design and implement AI capabilities supporting intelligent data characterization, classification, prioritization, and decision support. • Evaluate, optimize, and deploy open-weight foundation models appropriate for resource-constrained edge environments. • Develop efficient inference pipelines supporting heterogeneous compute environments ranging from embedded processors to workstation-class systems. • Implement Retrieval-Augmented Generation (RAG), semantic search, and knowledge retrieval capabilities where appropriate. • Design AI orchestration workflows supporting distributed inference across multiple edge devices. • Develop evaluation methodologies for AI accuracy, latency, resource utilization, and operational performance. • Implement model monitoring, observability, testing, and automated evaluation frameworks. • Collaborate with software engineers to integrate AI models into production software platforms. • Optimize models using quantization, pruning, distillation deployment technologies. • Support experimentation involving multimodal data sources, sensor-derived features, and structured mission data. • Develop AI governance practices including model evaluation, explainability, responsible AI, and secure deployment. • Document model development, evaluation results, and technical recommendations. • Support customer demonstrations and prototype evaluations.