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

We’re seeking a seasoned Senior AI/ML Engineer to help build robust, production-grade AI applications, intelligent automation, LLM-driven products, and enterprise AI platforms. The right candidate brings practical experience with Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, vector databases, and current AI frameworks. You’ll contribute throughout the product lifecycle—from translating business needs into architecture through implementation, integrations, and scalable deployment. We’re looking for engineers with a track record of shipping real AI products, not only tutorial projects or simple chatbot demos. Responsibilities - Architect, build, and launch production AI/ML solutions with Python and modern AI tooling. - Create sophisticated RAG workflows: document ingestion, preprocessing, chunking, embeddings, vector search, hybrid retrieval, reranking, and context-sensitive response generation. - Develop AI agents and multi-agent systems with LangChain, LangGraph, CrewAI, or custom orchestration solutions. - Connect applications to OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, and open-source LLMs. - Deliver chatbots, conversational interfaces, enterprise knowledge systems, and specialized AI copilots. - Use Pinecone, Qdrant, ChromaDB, FAISS, PostgreSQL with pgvector, and related vector-storage solutions. - Implement tool use, function calling, structured outputs, agent memory, planning, and human-in-the-loop approval flows. - Build MCP (Model Context Protocol) servers and integrations for external APIs, databases, and business platforms. - Develop document-intelligence capabilities for PDF parsing, OCR, extraction, summarization, and knowledge discovery. - Create natural-language-to-SQL products and AI-based analytics assistants. - Build backend services and REST APIs with FastAPI, Django, Node.js, or comparable technologies. - Apply prompt engineering, AI evaluation systems, guardrails, hallucination detection, and retrieval-quality improvements. - Embed AI features into web products built with React, Next.js, TypeScript, and related frontend tools. - Design secure, scalable architectures with authentication, RBAC, tenant separation, logging, and audit trails. - Improve LLM quality, latency, token efficiency, and operational cost. - Package applications with Docker and deploy on AWS, Azure, or other cloud platforms. - Establish dependable CI/CD, testing, monitoring, and deployment practices. Required Experience - 5+ years in professional software engineering, including strong hands-on Python development. - Demonstrated success delivering LLM-powered applications to production. - Strong command of RAG design, embeddings, vector search, retrieval approaches, reranking, and context handling. - Practical use of LangChain, LangGraph, LlamaIndex, or comparable AI orchestration frameworks. - Experience integrating OpenAI, Anthropic Claude, Gemini, or other LLM APIs. - Production experience with Pinecone, Qdrant, ChromaDB, FAISS, pgvector, or similar vector databases. - Solid grounding in machine learning, NLP, embeddings, semantic search, and deep-learning concepts. - Experience creating AI agents with tool calling, function execution, memory, planning, and multi-step workflows. - Strong backend expertise in FastAPI, Django, Flask, or Node.js. - Experience with PostgreSQL, MongoDB, Redis, Supabase, or other modern databases. - Understanding of REST APIs, async processing, microservices, and distributed systems. - Experience deploying applications on AWS or Microsoft Azure. - Strong Git, Docker, CI/CD, testing, and production-troubleshooting skills. - Ability to independently interpret requirements, make sound architectural choices, and produce maintainable code. - Strong written communication skills and comfort working with a remote engineering 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 - Background designing enterprise AI platforms or multi-tenant SaaS products. - Experience with agentic AI, autonomous workflows, and human-in-the-loop systems. - Familiarity with MLOps, model evaluation, experiment tracking, and observability. - Experience with AI security, prompt-injection defenses, PII detection, and access-control policies. - Experience building real-time AI solutions, streaming interfaces, or voice-enabled AI agents. - Knowledge of data engineering, ETL processes, and event-driven systems. - Integrations with Salesforce, HubSpot, Slack, Microsoft 365, or other business tools. - Experience in financial services, healthcare, e-commerce, or other enterprise sectors. - A portfolio, GitHub profile, or case studies showing hands-on AI product delivery. Expected Deliverables - Clean, scalable, maintainable Python code. - Production-ready RAG pipelines and AI-agent implementations. - Working AI applications with reliable API and database integrations. - Architecture documentation, technical documentation, and deployment guidance. - Automated tests and evaluation datasets for assessing AI-output quality. - Secure implementations with authentication, authorization, and logging. - Dockerized applications and deployment-ready configurations. - Consistent progress updates, thoughtful code reviews, and clear technical communication. How to Apply Please include: - A brief overview of your experience building production AI/ML applications. - Examples of RAG systems, AI agents, or LLM-powered products you have delivered; GitHub repositories or live demos are preferred. - The AI frameworks you use most often: LangChain, LangGraph, LlamaIndex, CrewAI, or others. - The vector databases you have deployed in production. - One challenging AI project you completed, including the architecture you selected. - Whether you are comfortable contributing to both AI/backend development and frontend integrations when needed. We’re interested in a long-term engineering partner focused on dependable AI products—not one-off prototypes. If you enjoy solving difficult technical problems and translating AI capabilities into useful business solutions, we’d be glad to hear from you.