Python & AI Engineer

Position Overview We are seeking a hands-on, meticulous Python & AI Engineer to contribute to the design, development, and evolution of our Business Analytics platform. You will work across the full backend stack, building RESTful APIs in Python FastAPI, integrating Large Language Models (LLMs), designing agentic workflows using LangGraph, implementing Retrieval-Augmented Generation (RAG) pipelines with Weaviate vector search, and managing analytical data stores in ClickHouse. You will collaborate closely with senior engineers and cross-functional stakeholders to ship features, improve platform reliability, and contribute to technology innovation initiatives. This is a high-impact, individual contributor role for someone who thrives at the intersection of backend engineering, applied AI, and data platform development. Responsibilities API Development & Backend Engineering by implementing RESTful API endpoints using FastAPI. LLM Integration & Prompt Engineering for content generation, insight extraction, structured data parsing, and intelligent document analysis. Build and extend AI agentic workflows using LangGraph defining state machines, tool nodes, and human-in-the-loop patterns. Develop tool functions that agents invoke for data retrieval, LLM calls, and external system interactions. Implement and maintain RAG pipelines using Weaviate as the vector database including document ingestion, chunking strategies, and hybrid search. Build MCP (Model Context Protocol) servers and tool-use patterns. Work with ClickHouse for analytical queries, data aggregation, and reporting. Write and maintain tests using pytest, covering API endpoints, service functions, and integration scenarios. Participate in code reviews, implement project conventions, and contribute to documentation (API docs, technical guides, runbooks). Monitor and resolve production issues, diagnosing failures across the API layer, LLM calls, vector search, and database queries. Qualifications 3 to 5 years of hands-on experience with Python development (FastAPI or similar frameworks). Working knowledge of R is a strong advantage. Solid understanding of RESTful API design, Pydantic data validation, and sync/await patterns in Python. Experience working with LLMs including prompt design and structured output handling. Experience with LangChain or LangGraph for building agentic AI workflows. Familiarity with vector databases (Weaviate, or similar) and RAG architecture. Working knowledge of SQL databases, ability to write analytical queries, manage schemas, and work with columnar stores like ClickHouse is a plus. Experience using AI-powered development tools such as GitHub Copilot or Claude Code for accelerated code generation, debugging, and navigation. Ability to perform end-to-end data science workflows: data collection, preprocessing, EDA, modeling, validation, and deployment. Basic understanding of frontend technologies like HTML, CSS, and JavaScript. Familiarity of R Shiny to present data insights and model outputs is bonus. Comfortable with Git workflows, code reviews, and task tracking tools (Jira). Soft Skills & Attributes Strong ownership approach who takes responsibility for features end-to-end, from design through deployment and support. Structured and disciplined approach to code quality, naming conventions, and project standards. Excellent communication skills with ability to discuss technical decisions with both engineering peers and business stakeholders. Curious and self-driven learner who can keep up with the rapidly evolving landscape of LLMs, AI agents, and retrieval systems. Proactive problem-solver who identifies root causes rather than applying surface-level fixes. Detail-oriented with a focus on correctness, observability, and clean error handling. Comfortable working independently while coordinating across a cross-functional team.