About the position We are seeking an exceptional Senior Full Stack AI Engineer to join our Genie team. You will be a key technical contributor responsible for designing, developing, and deploying end-to-end AI-powered applications that leverage Large Language Models (LLMs) and autonomous agent frameworks to revolutionize resource management. This role requires a unique blend of full-stack development expertise and deep AI/ML knowledge, with hands-on experience building production-grade GenAI and LLM-based solutions. You will work at the intersection of modern web development and cutting-edge AI technology, building scalable, intelligent systems that can reason, learn, and act autonomously to optimize resource allocation and management workflows. Responsibilities • Design, develop, and deploy agentic AI systems using frameworks like LangChain, LangGraph, CrewAI, or AutoGen • Build and optimize multi-agent workflows with capabilities including: Semantic search based Retrieval Augmented Generation (RAG) for context-aware responses • Tool usage and API orchestration • Context Engineering with memory and user personalisation • Implement LLM-powered features including intelligent resource recommendations, automated workflow optimization, and predictive analytics • Develop and fine-tune prompts for various LLM models (GPT-4, Claude, Llama, etc.) • Design guardrails, human-in-the-loop patterns, and response verification systems to prevent hallucinations and ensure accuracy • Drive architecture for AI observability, safety and evaluation (precision, F1, hallucination detection, arenaflex metrics). • Implement model evaluation frameworks and monitoring systems to track AI system performance • Build responsive, performant web applications using Next.js, React, and TypeScript • Design and implement RESTful APIs and GraphQL endpoints using Python (FastAPI/Flask) and Node.js • Develop backend services that integrate with LLM APIs (OpenAI, Anthropic, AWS Bedrock) • Create intuitive user interfaces that seamlessly incorporate AI capabilities • Implement real-time features using WebSockets for streaming LLM responses • Write clean, maintainable, well-documented code following best practices and design patterns • Deploy and manage applications on AWS services including: Lambda, ECS/EKS, S3, API Gateway, SageMaker, Bedrock • DynamoDB, RDS, ElastiCache • CloudWatch, X-Ray for monitoring and observability • Implement arenaflex/CD pipelines for automated testing and deployment • Should have fair understanding of MLOPS • Design scalable, fault-tolerant architectures that can handle high-volume AI workloads • Optimize infrastructure costs while maintaining performance and reliability • Collaborate with product managers, designers, and stakeholders to translate business requirements into technical solutions • Participate in code reviews, architectural discussions, and technical design sessions • Mentor junior engineers and share best practices for AI-driven development • Stay current with the latest advancements in LLMs, agentic AI, and machine learning techniques • Document system architectures, API specifications, and implementation details • Contribute to the evolution of our AI development standards and practices Requirements • Programming Languages: 5+ years of professional experience with: Python (advanced proficiency) - Langraph, Langchain, NumPy, Pandas, scikit-learn • TypeScript/JavaScript (ES6+) • Strong understanding of object-oriented and functional programming paradigms • Full Stack Development: 4+ years of experience with: Frontend: Next.js, React, React Hooks, Context API, TailwindCSS, Shadcn/UI • Backend: Node.js, Fastify, FastAPI, Flask • APIs: RESTful design, GraphQL, WebSocket implementation • Databases: PostgreSQL, MongoDB, Redis • AWS: EC2, Lambda, S3, ECS/EKS, SageMaker, Bedrock, CloudWatch • arenaflex/CD: GitHub Actions, Jenkins, GitLab arenaflex • AI/ML Expertise: 2+ years hands-on experience with: LLM Integration: OpenAI API, Anthropic Claude, AWS Bedrock, Azure OpenAI • Agentic Frameworks: LangChain, LangGraph, CrewAI, AutoGen, Claude SDK or similar • Observability and Traceability: Arize Pheonix, Langfuse, LangSmith, AgentOps • RAG Systems: Building retrieval pipelines, chunking strategies, embedding generation • Vector Databases: Pinecone, Weaviate, FAISS, ChromaDB, or Qdrant • ML Libraries: TensorFlow, PyTorch, Hugging Face Transformers • Prompt Engineering: Advanced techniques for optimization and consistency • Bachelor's or Master's degree in Computer Science, Engineering, AI/ML, or related field • 5-7 years of professional software engineering experience • 2+ years of hands-on experience building production LLM/GenAI applications • Proven track record of deploying and scaling AI-powered applications in production environments • Experience with the complete software development lifecycle (SDLC) • Strong understanding of software architecture patterns and system design principles. Nice-to-haves • Experience with model fine-tuning and custom model deployment • Knowledge of machine learning algorithms, neural networks, and deep learning architectures • Familiarity with MLOps practices and tools (MLflow, Weights & Biases, Kubeflow) • Experience with streaming data pipelines (Kafka, Kinesis) • Understanding of AI safety, ethics, and responsible AI practices • Contributions to open-source AI/ML projects Benefits • Work remotely, Yes thats right we are proud remote first company • Opportunity to work on cutting-edge AI technology with real-world impact • Dedicated AI Coding assistant • Collaborative team environment with talented engineers and researchers • Competitive salary and equity compensation • Comprehensive health, dental, and vision insurance • Modern tech stack and tools Apply tot his job