Full Stack Engineer

• We are seeking a Senior AI Engineer (Full stack) with advanced Python skills to join our team building and advancing the Luma platform-an AI-Native Multimodal Research Platform for Scientific Intelligence. A platform that helps customers analyze and configure data within their system
• This role offers the opportunity to work on cutting-edge AI/ML technology, architecting scalable microservices, and delivering production-ready systems that integrate with enterprise data platforms
• You will build AI agents that perform real work-systems that plan tasks, call tools, execute workflows, interact with APIs, and integrate with real-world data sources
• You'll be working in a collaborative, agentic coding environment where modern development tools support your workflow, enabling rapid iteration while maintaining high code quality standards
• Design and implement AI agent workflows and tooling using LangChain/LangGraph, enabling AI models to plan actions, call tools, use APIs, search information, and reliably complete multi-step workflows
• Build and maintain the tools, function interfaces, and system connectors that AI agents use to interact with databases, document stores, enterprise apps, and external APIs
• Ensure AI agents operate safely, follow rules, respect permissions, and reliably execute within defined constraints
• Lead and execute the design and implementation of core workflow orchestration and tooling features, including automated tasks and background processes
• Build scalable FastAPI services with well-defined RESTful APIs and real-time streaming endpoints
• Create modular, reusable service components with strong authentication, error handling, and pagination patterns
• Develop and guide React frontend components for real-time interactions and data visualization
• Implement multi-tenant architecture with secure isolation, resource boundaries, and long-term scalability
• Provide technical guidance to other engineers during implementation, ensuring high-quality, maintainable solutions
• Evaluate risk when implementing new features or refactoring, and propose safe rollout strategies
• Clean Architecture principles with clear separation of concerns
• Microservices design patterns including service discovery, API gateways, and interservice communication
• Multi-tenancy architecture with schema-based isolation
• Event-driven architecture with message queues and async processing
• Subprocess isolation patterns for credential management and security boundaries
• Influence architectural direction across teams, helping bring clarity and structure to ambiguous problems
• Architect robust AI agent execution layers that ensure determinism, observability, and reliable stepwise execution
• Write comprehensive automated tests using pytest and Jest, including integration and behavior-driven tests
• Implement structured logging, correlation IDs, and observability patterns to ensure system clarity and operability
• Contribute to and improve CI/CD pipelines with automated testing, linting, and deployment workflows
• Set up effective monitoring and alerting for production systems
• Lead or support critical incident resolution with calm, context-driven decision-making
• Drive platform-wide improvements in performance, reliability, and technical quality
• Exercise independent judgment in methods, techniques, and evaluation criteria to ensure robust outcomes
• Instrument AI agent systems with monitoring, tracing, and guardrails to ensure safe and predictable behavior in production
• Document architectural decisions, engineering patterns, and approaches that become long-term references for the team
• Provide approach summaries and technical proposals before major implementations to ensure alignment with product and engineering partners
• Participate in planning and estimation, applying deep technical judgment and strong product awareness
• Mentor engineers, raise team capabilities, and guide others through complex engineering workflows (feature branches, PRs, ticket management)
• Build relationships across engineering and product groups, influencing roadmaps and cross-team initiatives
• Communicate risks, challenges, and opportunities proactively and clearly to stakeholders
• Document and evangelize best practices for safe, reliable, and maintainable AI agent design

Communication skills Collaboration and teamwork FastAPI, * We are looking for people who have 10+ years of professional software development experience, including significant experience owning and delivering large-scale technical systems

• You should bring the ability to design durable architectures, independently lead high-impact engineering efforts, and mentor other engineers while maintaining exceptional coding standards
• You should enjoy architecting clean, resilient services, solving complex systems problems, and shaping long-term technical direction for the areas you support
• Strong understanding of dependency injection, clean architecture, and functional programming concepts
• FastAPI experience building production RESTful APIs, streaming endpoints (SSE), and async request handling
• Experience building AI agents using LangChain/LangGraph, including tool creation, step planning, function calling, retrieval workflows, and reliable agent-state management
• Strong PostgreSQL expertise (including performance tuning and schema design) and SQLAlchemy
• Experience designing and scaling microservices in production environments
• Experience building safe execution environments and guardrails for AI decision-making
• Expert-level Python 3.11+ with deep understanding of async/await, type hints, and modern Python best practices
• Ability to assess engineering risk, propose rollout strategies, and make high-impact architectural decisions
• React & TypeScript with modern hooks and state management patterns (Redux/Context)
• Familiarity with Jest for robust frontend testing practices
• Experience with Webpack Module Federation and micro-frontend architectures
• Ability to design responsive, maintainable UI components using SCSS/CSS
• Familiarity withLLM serving endpoints(Databricks, OpenAI, Anthropic, or similar)
• Experience with agent orchestration, tool creation, and multi-step reasoning workflows
• Proven experience buildingLLM-powered applications with frameworks like LangChain, LangGraph, or similar
• Understanding of Retrieval-Augmented Generation (RAG)patterns and vector embeddings
• Understanding of Model Context Protocol (MCP)for tool integration
• Knowledge of streaming responses, callback systems, and real-time feedback mechanisms
• LangChain & LangGraphexpertise for building AI agent workflows, tool orchestration, and LLM integration
• Production Kubernetes experience with Helm charts and orchestration
• Experience with Databricks or similar cloud data platforms
• LangChain/LangGraph production implementations