Ssr. Fullstack Engineer
Summary
We are seeking a semi-senior Ssr. Fullstack Engineer B. to design and build AI-driven full-stack solutions. This role focuses on agentic AI and machine learning systems, backend services in C# /.NET and Python, modern JavaScript frontends, and Azure cloud integration. The position offers hands-on work with multi-agent orchestration, RAG pipelines, and enterprise Copilot deployments. The role is ideal for an engineer who balances pragmatic delivery with scalable architecture, documents decisions clearly, and collaborates across data science and product teams.
Responsibilities
Design and implement multi-agent AI systems using frameworks such as LangChain, AutoGen, and CrewAI Build RAG (Retrieval-Augmented Generation) pipelines with vector databases like Pinecone or Weaviate Implement agent orchestration patterns and inter-agent communication protocols for distributed AI workflows Develop LLM fine-tuning workflows and optimize prompt engineering for production use Design and deploy Microsoft Copilot Foundry solutions with custom knowledge bases and integration workflows Develop backend services using C# /.NET (ASP.NET Core, Entity Framework, SignalR, Minimal APIs) and Python (FastAPI, Django, Flask) Implement microservices and containerized deployments using Docker and event-driven architectures with Azure Service Bus or RabbitMQ Integrate Azure services including Azure Functions, Azure Logic Apps, Azure Cognitive Services, Azure OpenAI Service, and Azure Data Factory Build and maintain CI/CD pipelines and infrastructure as code using Azure DevOps, ARM/Bicep, or Terraform Mentor junior developers, document architecture decisions, and collaborate with product managers and data scientists Balance technical debt with feature delivery while considering scalability, maintainability, code quality, testing, and documentation. Implement monitoring and observability using Application Insights. Apply Git workflow management and branching strategies in collaborative development environments.
Requirements
Proven experience designing and implementing multi-agent AI systems and RAG pipelines using LangChain, AutoGen, or CrewAI Hands-on experience with vector databases such as Pinecone or Weaviate Experience with LLM fine-tuning and prompt engineering optimization Experience developing AI-powered decision engines or autonomous task execution systems. JavaScript Frameworks: Proficiency in modern JavaScript frameworks (e.g., React, Angular, Vue.js) for developing responsive and dynamic frontend applications. Strong backend development experience with C# /.NET (ASP.NET Core, Entity Framework, SignalR, Minimal APIs) Basic knowledge of Python and familiarity with common backend or data/ML libraries such as FastAPI, Django, Flask, Pandas, NumPy, or Scikit-learn. Experience building microservices, containerizing with Docker, and implementing event-driven architectures (Azure Service Bus, RabbitMQ) Familiarity with Azure platform services: Azure Functions, Azure Logic Apps, Azure Cognitive Services, Azure OpenAI Service, and Azure Data Factory Experience with Azure DevOps for CI/CD and YAML pipeline configuration Experience with Infrastructure as Code using ARM templates, Bicep, or Terraform Strong problem-solving approach, ability to translate AI concepts into business terms, and experience documenting architecture and trade-offs Experience with monitoring and observability tools, especially Application Insights. Experience with Git workflow management and branching strategies. Ability to understand business requirements before jumping to technical solutions and advocate for MVP approaches with iterative improvement. Strong collaboration skills with data scientists, product managers, business stakeholders, and cross-functional teams. Commitment to code quality, testing, proper documentation, scalability, and maintainability. Interest in staying current with the rapidly evolving AI/ML landscape. \n \nEngagement & Logistics Engagement Length: 12+ months. Time Zone: 10:30 - 18:30 EST. Overtime Required: On-call –Expected frequency: 1 week every 6. Equipment: Provided by the client. Selection process Meeting with Resilient Co. team. Glider Code assessment Project interview (Cultural fit and tech review)