mcp jobs in San Diego

The AI Scientific Software Engineer will develop MARIE, an AI-powered scientific companion within BIOVIA's Pipeline Pilot platform, focusing on prompt engineering, agentic AI frameworks, and AI safety mechanisms. Responsibilities include designing and iterating on prompts for improved reasoning and factuality, building multi-step agentic workflows with tool calling and memory management, and implementing guardrails and validation systems.…See more The role requires a PhD in Life Sciences or Computer Science with 3+ years of software development experience, strong LLM fundamentals knowledge, hands-on experience with RAG systems and frameworks like LangChain/LangGraph, and familiarity with pharmaceutical and biotech workflows.

Design and build production-ready agentic AI applications that automate mission-critical workflows. You will implement agent orchestration frameworks, tool-calling patterns, and multi-agent interactions using LLM platforms like AWS Bedrock and OpenAI, working in fast 4-week prototype cycles with a small high-performing team.…See more The role requires end-to-end technical ownership from design through deployment, including prompt engineering, retrieval patterns (RAG/GraphRAG), and observability implementation. You'll collaborate with product leads and solution architects to deliver reliable, cost-effective agent-based solutions that solve client challenges.

Staff Engineer role focused on architecting and developing full-stack applications with AI-native development at its core. Responsibilities include designing RESTful APIs, managing databases, and critically—directing AI coding agents (Claude, Cursor, Copilot) across the delivery lifecycle, including prompt engineering, agent workflow design, and tracing/debugging agent outputs.…See more Requires 8+ years with complex codebases, full-stack expertise (Java/Go/Python, React, REST APIs), and demonstrated proficiency using AI coding tools as a primary delivery vehicle, not just a helper.

You will develop AI-powered scientific software for MARIE, an AI companion within BIOVIA's Pipeline Pilot platform serving pharmaceutical and biotech researchers. The role focuses on prompt engineering, agentic AI frameworks, and AI safety mechanisms—designing and optimizing LLM-based workflows for multi-step scientific tasks.…See more You'll implement RAG systems, semantic search, vector databases, and guardrails while collaborating across engineering, QA, product, and technical teams using Agile practices. The position requires a PhD in Life Sciences or Computer Science, 3+ years of software development, and hands-on experience with LLMs, agentic frameworks like LangChain, and prompt optimization.

Design, build, and deploy production agentic AI solutions powered by Claude for enterprise clients, from proof-of-concept through production. Implement multi-agent systems that automate business processes, integrate with enterprise tools, and operate within defined autonomy and guardrails.…See more Modernize existing AI/ML platforms with generative AI capabilities including RAG and agent-based orchestration. Advise clients on generative AI adoption strategy, responsible AI practices, and model selection while partnering with technology, data, and business stakeholders to scope and deliver solutions.

Lead end-to-end technical architecture for complex PIM, PXM, and commerce SaaS implementations, translating business requirements into scalable solution architectures. Design data models, integration patterns, and system landscapes across PIM, DAM, ERP, and commerce platforms, with hands-on technical leadership to delivery teams on configuration, custom development, and integration.…See more Own technical integration strategy using APIs, services, and event-driven patterns; act as technical authority for risk identification and architectural decisions. Stay current on Agentic Commerce and GenAI trends to automate product content supply chains and drive AEO/GEO strategies for LLM syndication.

Lead ServiceNow AI implementation projects as an architect-manager, designing and deploying AI solutions (NOW Assist, Agentic, AI Control Tower) with hands-on expertise in prompt engineering, LLM orchestration, and RAG techniques. Configure Moveworks for automated ticket resolution and integrate multiple AI models within ServiceNow workflows.…See more Conduct client design sessions, manage project delivery across waterfall and agile models, and lead technical teams while supporting pre-sales efforts.

Lead security operations and threat detection engineering for enterprise clients using Google SecOps (Chronicle SIEM and Siemplify SOAR). Design and deploy log ingestion pipelines, develop threat detection rules, translate SOC processes into automated playbooks, and manage integrations across security platforms.…See more Mentor junior SOC engineers and collaborate with threat detection teams to reduce alert fatigue and scale response capabilities.

Design, build, and operate production-quality agentic AI systems and developer tooling at scale. Lead multi-agent orchestration, Model Context Protocol (MCP) integration, prompt engineering for structured output, and CI/CD automation for code review and testing.…See more Partner with engineering teams on discovery, rapidly prototype and validate capabilities, then own the full lifecycle from implementation through production monitoring. Mentor engineers on agentic design patterns and communicate technical tradeoffs to stakeholders.

Senior Software Engineer responsible for designing and communicating architectural decisions across technical and non-technical teams at a healthcare technology company. Will reduce technical debt, improve developer experience, provide code and design reviews, and mentor engineers in AI-enabled development practices.…See more Requires 8+ years of software engineering experience with strong fundamentals in production systems, APIs, distributed systems, cloud-native applications, CI/CD, and observability. Should demonstrate leadership in technical initiatives, influence without formal authority, and hands-on proficiency with AI-assisted development tools while maintaining code quality accountability.

Lead a team of security engineers (staff, senior staff, principal levels) owning product security across Intuit's ecosystem, including security reviews, design consults, and risk evaluations. Transform security processes from manual to automation/agent-first, defining baseline controls and security standards for cloud platforms (AWS, GCP, Azure) while raising the bar for AI/agentic systems.…See more Partner with business and engineering leaders to surface risks early, inform decisions, and drive adoption of security controls across large organizations. Requires 8+ years in security engineering, 3+ years managing managers, deep technical expertise in application security and threat modeling, and demonstrated experience rebuilding security programs with hands-on automation.

Design, implement, and optimize real-time embedded modem firmware across protocol layers and drivers while meeting strict latency, memory, and power constraints. You will own end-to-end feature delivery from requirements through on-target bring-up, apply rigorous data-structure and algorithm design, and pioneer AI-native development practices by integrating AI coding agents, LLM-based code review, and automated test synthesis into daily workflows.…See more Debug complex multi-layer issues on target hardware using JTAG, logic analyzers, and AI-assisted log/crash analysis. Mentor peers on embedded fundamentals and AI-native engineering techniques while contributing to design reviews and engineering standards.

Sr. Engineer responsible for designing, building, and deploying production-grade AI platforms and solutions centered on LLMs, RAG, and agentic workflows.…See more The role spans full-stack development—from backend services and APIs to cloud-native infrastructure on Kubernetes—with emphasis on enterprise search, retrieval optimization, and AI application integration. Must have strong programming skills across Python, Java, C#/.NET, Rust, TypeScript/JavaScript, and proven experience architecting and operating scalable, production-ready AI systems.

The AI SW Integration Engineer will develop backend tools and services that automate test generation, improve requirements traceability, and streamline engineering workflows across teams. The role requires strong expertise in generative AI and large language models (LLMs), with hands-on experience designing and deploying agentic AI systems end-to-end.…See more You will integrate tools and databases via REST APIs, parse structured documents, and build automation solutions using Python and CI/CD pipelines. The ideal candidate brings 3–5 years of production experience developing automation or integration tools, plus familiarity with RAG, MCP, and requirements management workflows.

As a Forward Deployed Engineer IV in Applied AI at Google Cloud, you will lead end-to-end engineering for production conversational AI systems, transforming prototypes into scalable agentic workflows deployed at customer sites. You'll architect multi-agent systems using frameworks like ReAct, optimize RAG implementations, debug agent logic across microservices, and connect AI systems to enterprise infrastructure.…See more The role requires 8+ years of software development (Python or similar), experience with infrastructure-as-code (Terraform), cloud platform deployment (GCP), and hands-on full-stack application development. You'll travel up to 50% and work directly with customers to establish production AI journeys while identifying patterns that feed back into product improvements.

Design and build AI agents and full-stack web applications that automate enterprise workflows, with expertise in agentic AI frameworks, LLM orchestration, and generative AI integration. Architect a multi-agent platform enabling PM and engineering agents to exchange plans and context, while developing backend services in C#/.NET/Python/TypeScript and modern Angular/React frontends that connect to enterprise systems like Jira, Microsoft 365, and SQL/NoSQL databases.…See more Define agentic engineering standards including tool contracts, prompt management, guardrails, and agent evaluation. Requires hands-on experience with LLM application development, RAG, tool calling, prompt engineering, agentic runtimes (LangGraph, AutoGen, n8n), and full-stack enterprise application development on AWS or Azure.

Design and build AI agents that automate workflows within a multi-agent platform, enabling PM and engineering agents to exchange plans and context over shared program data. Develop full-stack web applications with generative AI functionality—conversational interfaces, natural-language querying, automated summarization, and in-context recommendations—using C#, .NET, Python, TypeScript, Angular/React, and integrations with Jira, Microsoft 365, Confluence, and SQL/NoSQL stores.…See more Define agentic engineering standards including tool contracts, MCP servers, prompt management, memory, guardrails, human-in-the-loop approval, and evaluation harnesses. Requires hands-on experience with LLM application development, agentic runtimes like LangGraph or AutoGen, full-stack enterprise development, and cloud deployment on AWS or Azure.

Join Gadriel AI as an AI Developer to design, build, and ship features across their AI code validation platform end-to-end. You'll work primarily with modern AI coding assistants (Claude, Cursor, Windsurf) as your development environment, build integrations with AI tools and CLIs, contribute to backend services and validation logic, and participate in architecture decisions at an early-stage startup.…See more The role requires strong full-stack engineering fundamentals across TypeScript/JavaScript and Python, real hands-on experience with AI coding assistants, CLI and developer tooling experience, and familiarity with security concepts like SAST and SCA. You'll move fast, iterate on user feedback, and help shape product direction in a high-autonomy, founder-led environment.

Lead the design, governance, and technical implementation of an enterprise API and AI gateway platform serving internal and external consumers. Define solution standards, security controls, compliance protocols aligned to financial services regulations, and LLM integration patterns across Apigee X, MCP servers, and multiple AI providers.…See more Manage a team through API modernization and AI gateway buildout while actively contributing hands-on engineering on proxies, policies, and MCP integrations when needed.

Staff Engineer role driving Generative AI transformation across embedded software and engineering infrastructure at Qualcomm. Responsible for executing GenAI workstreams—converting engineering use cases into production-ready AI-enabled workflows for code generation, review, debugging, test automation, and documentation.…See more Will build reusable agents, prompts, MCP integrations, and evaluation flows; partner with embedded, platform, and software teams to onboard and increase adoption of secure, measurable GenAI solutions. Requires 4+ years software engineering experience, 3+ years hands-on GenAI/LLM application development, and strong proficiency in Python, C, C++, or Go with embedded systems familiarity.

Lead Qualcomm's GenAI transformation for embedded and software engineering, building reusable AI agents, agentic workflows, and developer productivity tools that scale across teams. Partner with platform and engineering teams to establish secure AI practices, governance models, and metrics while serving as a technical thought leader who shapes the organization's transition to AI-native engineering workflows.…See more Requires Principal-level technical leadership with deep expertise in generative AI, LLM-based systems, and hands-on experience deploying GenAI solutions in complex engineering environments. Collaborate on code generation, code review, test automation, and release readiness use cases while driving measurable productivity and quality improvements.

Design, implement, and optimize real-time embedded modem firmware across protocol layers and drivers while meeting strict latency, memory, and power constraints. Pioneer AI-native development practices by integrating AI coding agents, LLM-based code review, and automated test synthesis into daily workflows to accelerate delivery and debugging.…See more Own end-to-end feature delivery from requirements through on-target bring-up, and debug complex multi-layer hardware issues using AI-assisted analysis. Requires deep expertise in modern C/C++, embedded systems (DSP/Arm architectures), RTOS internals, data structures, and hands-on target hardware debugging, combined with practical experience using AI coding assistants and agentic tools.

Design and build production AI solutions including copilots, agents, RAG applications, and workflow automations on Azure OpenAI, Claude, and Microsoft platforms. Write custom code in Python, JavaScript/TypeScript, or C# and leverage low-code platforms like Power Automate and Logic Apps where appropriate, following solid engineering practices (version control, testing, CI/CD, AI output evaluation).…See more Integrate solutions with enterprise systems and APIs with security-first design, own projects end-to-end from deployment through adoption and improvement, and work with security, architecture, governance, and compliance teams to ensure production readiness. Communicate clearly to both technical and business audiences, document designs, and coach teammates on AI capabilities, limits, and risks.

Design, build, and ship LLM-powered capabilities end to end—from prototyping and fine-tuning models to deploying production agents and retrieval systems. Own the full stack: prompt and context engineering, multi-step agent design with tool calling, RAG systems (embeddings, chunking, hybrid search, reranking), fine-tuning on multi-GPU with LoRA/QLoRA, evaluation and tracing infrastructure, and clean APIs for other engineers.…See more Work in a secure, distributed environment where the platform runs on customer compute, cloud, or hybrid setups, requiring expertise with both commercial and self-hosted models.