Senior AI/ML Engineer – RAG, LLMs, AI Agents & Python

We are looking for an experienced Senior AI/ML Engineer to join our development team and work on building production-ready AI applications, intelligent automation systems, LLM-powered products, and enterprise AI solutions. The ideal candidate should have strong hands-on experience with Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, vector databases, and modern AI frameworks. You will work across the complete AI product development lifecycle, from understanding business requirements and designing system architecture to implementing AI workflows, integrating backend services, and deploying scalable applications. We are particularly interested in engineers who have already built and deployed real-world AI applications, rather than candidates whose experience is limited to tutorials or basic chatbot implementations. What you'll do Design, develop, and deploy production-ready AI/ML applications using Python and modern AI frameworks. Build advanced RAG pipelines, including document ingestion, preprocessing, chunking, embedding generation, vector search, hybrid retrieval, reranking, and context-aware response generation. Develop intelligent AI agents and multi-agent workflows using LangChain, LangGraph, CrewAI, or custom orchestration frameworks. Integrate LLM providers such as OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, and open-source models. Build AI chatbots, conversational assistants, enterprise knowledge-management systems, and domain-specific AI copilots. Work with vector databases such as Pinecone, Qdrant, ChromaDB, FAISS, and PostgreSQL with pgvector. Implement tool calling, structured outputs, function calling, agent memory, planning, and human-in-the-loop approval workflows. Develop MCP (Model Context Protocol) servers and integrations to connect AI assistants with external APIs, databases, and business applications. Design document intelligence solutions for PDF processing, OCR, information extraction, summarization, and knowledge discovery. Develop natural-language-to-SQL solutions and AI-powered analytics assistants. Build backend services and REST APIs using FastAPI, Django, Node.js, or similar technologies. Implement prompt engineering, AI evaluation frameworks, guardrails, hallucination detection, and retrieval-quality optimization. Integrate AI capabilities into modern web applications using React, Next.js, TypeScript, and related frontend technologies. Design secure and scalable AI architectures with authentication, RBAC, tenant isolation, logging, and audit trails. Optimize LLM applications for response quality, latency, token consumption, and operational cost. Containerize applications using Docker and deploy production workloads using AWS, Azure, or other cloud platforms. Establish CI/CD pipelines, monitoring, testing, and reliable deployment processes. Required experience 5+ years of professional software development experience, with strong hands-on Python development experience. Proven experience building and deploying LLM-powered applications in production. Strong understanding of RAG architecture, including embeddings, vector search, retrieval strategies, reranking, and context management. Practical experience with LangChain, LangGraph, LlamaIndex, or similar AI orchestration frameworks. Experience integrating OpenAI, Anthropic Claude, Gemini, or other LLM APIs. Hands-on experience with vector databases such as Pinecone, Qdrant, ChromaDB, FAISS, or pgvector. Strong understanding of machine learning, NLP, embeddings, semantic search, and deep learning fundamentals. Experience building AI agents with tool calling, function execution, memory, planning, and multi-step workflows. Strong backend development experience with FastAPI, Django, Flask, or Node.js. Experience working with PostgreSQL, MongoDB, Redis, Supabase, or other modern databases. Good understanding of REST APIs, asynchronous processing, microservices, and distributed systems. Experience deploying applications using AWS or Microsoft Azure. Proficiency with Git, Docker, CI/CD, testing, and production debugging. Ability to independently understand technical requirements, make architectural decisions, and deliver maintainable solutions. Excellent written communication and the ability to work in a remote development team. Preferred technology stack Programming Languages Python TypeScript JavaScript SQL AI / ML / LLM OpenAI API Anthropic Claude API Google Gemini AWS Bedrock Hugging Face TensorFlow / PyTorch Scikit-learn NLP and Deep Learning AI Frameworks & Agent Development LangChain LangGraph LlamaIndex CrewAI MCP (Model Context Protocol) Vercel AI SDK RAG & Vector Databases Pinecone Qdrant ChromaDB FAISS PostgreSQL / pgvector Elasticsearch / OpenSearch Backend & APIs Python FastAPI Django Node.js NestJS REST APIs GraphQL Frontend Development React.js Next.js TypeScript Tailwind CSS Material UI Cloud & DevOps AWS Azure Docker Kubernetes Serverless GitHub Actions CI/CD Nice to have Experience designing enterprise-grade AI platforms and multi-tenant SaaS applications. Experience with agentic AI architectures, autonomous workflows, and human-in-the-loop systems. Knowledge of MLOps, model evaluation, experiment tracking, and observability. Experience implementing AI security, prompt-injection protection, PII detection, and access-control policies. Experience with real-time AI applications, streaming responses, and voice-based AI agents. Knowledge of data engineering, ETL pipelines, and event-driven architectures. Experience integrating third-party platforms such as Salesforce, HubSpot, Slack, Microsoft 365, and other business tools. Experience working with financial services, healthcare, e-commerce, or other enterprise domains. A portfolio of AI products, GitHub repositories, or technical case studies demonstrating real implementation experience. Expected deliverables Well-structured, scalable, and maintainable Python code. Production-ready RAG pipelines and AI agent implementations. Functional AI applications with proper API and database integrations. Technical documentation, architecture diagrams, and deployment instructions. Automated tests and evaluation datasets for validating AI output quality. Secure implementations with appropriate authentication, authorization, and logging. Dockerized applications and deployment-ready configurations. Regular progress updates, code reviews, and clear technical communication. How to apply Please include the following information in your proposal: Briefly describe your experience developing production-ready AI/ML applications. Share examples of RAG systems, AI agents, or LLM-powered applications you have built. GitHub links or live demos are preferred. Which AI frameworks do you work with most frequently: LangChain, LangGraph, LlamaIndex, CrewAI, or others? Which vector databases have you implemented in production? Describe one technically challenging AI project you delivered and the architecture you used. Are you comfortable working on both AI/backend development and frontend integrations when required? We are looking for someone interested in long-term collaboration and building reliable AI products, not simply completing isolated prototypes. If you enjoy solving complex engineering problems and turning AI capabilities into practical business applications, we'd love to hear from you.