Full-Stack AI Engineer – LLMs, Agentic AI & Intelligent Systems

Full-Stack AI Engineer – LLMs, Agentic AI & Intelligent SystemsAbout the RoleWe are looking for a talented and motivated Full-Stack AI Engineer to join our growing technology team and help design, develop, and deploy innovative AI-powered applications.This is a hands-on engineering role focused on building production-ready AI systems that solve real-world business problems. You will work across the full application stack, developing intelligent AI workflows, backend services, data processing pipelines, and integrations with leading large language models (LLMs).The ideal candidate combines strong software engineering fundamentals with practical experience in Generative AI, agentic workflows, Retrieval-Augmented Generation (RAG), natural language processing (NLP), and modern AI frameworks.You will have the opportunity to work with cutting-edge AI technologies, experiment with emerging approaches, and contribute directly to the architecture and development of scalable, reliable AI applications.We value engineers who enjoy solving complex problems, take ownership of their work, and understand that building successful AI products requires more than simply integrating LLM APIs.Key Responsibilities1. AI Application & Full-Stack DevelopmentDesign, develop, and maintain end-to-end AI-powered applications and intelligent workflows.Build scalable backend services, RESTful APIs, and background processing components using Python and Django.Develop modular, maintainable applications following object-oriented programming principles and established software design patterns.Integrate AI capabilities into existing applications, databases, and business workflows.Collaborate on frontend development and API integrations where required.2. Generative AI, LLMs & Agentic WorkflowsDesign and implement agentic AI workflows capable of reasoning, planning, using tools, and executing multi-step tasks.Build applications using commercial and open-source LLMs, selecting appropriate models based on accuracy, latency, capability, and cost.Develop reliable tool-calling, function-calling, and orchestration workflows to integrate AI agents with external services, APIs, and databases.Apply prompt engineering and context engineering techniques to improve model performance, relevance, and reliability.Design and integrate Model Context Protocol (MCP) servers to expose tools, resources, and business functionality to AI applications.3. RAG, Knowledge Retrieval & Data EngineeringDesign, implement, and optimize Retrieval-Augmented Generation (RAG) pipelines for enterprise knowledge retrieval and question-answering applications.Work with structured and unstructured data, including documents, spreadsheets, databases, and other business information sources.Build document ingestion, parsing, chunking, embedding, indexing, and retrieval pipelines.Implement semantic search, hybrid search, metadata filtering, and reranking techniques to improve retrieval quality.Work with SQL, NoSQL, vector databases, and graph databases to support AI-driven applications.Develop data processing and transformation workflows to prepare information for AI consumption.4. Backend Architecture, Integration & Production OperationsDesign and develop background jobs, asynchronous processing services, and message-driven workflows.Integrate external APIs, databases, and third-party services into AI applications.Work with Docker, GitHub, and modern development workflows to build and deploy applications.Contribute to application architecture, testing, documentation, and ongoing maintenance.Required Skills & ExperienceSoftware EngineeringStrong professional programming experience with Python.Experience building backend applications and RESTful Web APIs using Django, Django REST Framework, or similar Python frameworks.Strong understanding of object-oriented programming (OOP), SOLID principles, software architecture, and design patterns.Good understanding of asynchronous programming, background processing, and message-driven architectures.Experience with Docker, Git, GitHub, and modern software development practices.Solid understanding of relational database design and proficiency with SQL.Generative AI & LLM EngineeringPractical experience developing applications using large language models (LLMs).Experience designing and implementing agentic AI systems and multi-step AI workflows.Strong understanding of prompt engineering, context engineering, tool calling, and LLM orchestration.Familiarity with MCP servers and AI agent architectures.Experience integrating multiple LLM providers and working with open-source language models.Knowledge of AI evaluation methodologies and the ability to build automated evaluation pipelines.RAG, Databases & Data ProcessingHands-on experience building RAG systems, including embedding generation, vector indexing, and semantic retrieval.Working knowledge of vector databases such as Qdrant, Pinecone, Weaviate, Chroma, or equivalent technologies.Understanding of SQL and NoSQL databases, with familiarity with graph databases such as Neo4j.Experience processing structured and unstructured data.Understanding of document ingestion, retrieval optimization, and data transformation techniques.Machine Learning & NLPGood understanding of machine learning and natural language processing concepts.Experience with TensorFlow, PyTorch, scikit-learn, or similar frameworks.Familiarity with embeddings, transformer architectures, and modern NLP techniques.Ability to evaluate and apply appropriate machine learning or AI approaches to business problems.Professional SkillsStrong analytical thinking, problem-solving, and debugging skills.Ability to design practical, reliable solutions rather than relying solely on experimental prototypes.Commitment to writing clean, maintainable, well-tested, and documented code.Ability to work independently, take ownership of deliverables, and collaborate effectively with a technical team.Enthusiasm for learning and experimenting with emerging AI technologies.Nice to haveThe following experience would be advantageous but is not essential:Document AI, OCR, and intelligent document processing, including extraction from PDFs, scanned documents, spreadsheets, and complex layouts.Experience building AI applications for the financial services, investment management, or legal sectors.Familiarity with other object-oriented languages, particularly C#/.NET or Java and modern Frontend Frameworks like Typescript, React or similar.Experience with message brokers such as RabbitMQ, distributed task queues, or similar technologies.Familiarity with fine-tuning, model serving, inference optimization, or deploying open-source LLMs.Why Join Us?You will have the opportunity to work on challenging, real-world AI projects and play an important role in shaping how advanced AI technologies are incorporated into business applications.This position offers a combination of hands-on software engineering, AI experimentation, architectural design, and product development, providing the opportunity to make a meaningful contribution while continuously expanding your expertise in a rapidly evolving field.