QX Impact - Software Engineer - Generative AI System

Role Overview

QX Impact is looking for a senior engineer to design, build, and ship production Generative AI systems. You will own applications end to end from architecture and data flow through deployment, evaluation, and iteration, focusing on reliability and impact rather than just prototypes. This is a core software engineering role applying LLMs, retrieval, and agents to solve concrete problems in finance, supply chain, and manufacturing.

Responsibilities

• Design, build, and ship production GenAI applications end to end owning architecture, data flow, deployment, evaluation, and iteration.
• Write clean, well-tested Python and build robust backend services and APIs (FastAPI/Flask) that serve LLM-powered features reliably at scale.
• Build retrieval and agentic systems: RAG pipelines over structured and unstructured data, tool-calling agents, and multi-agent workflows using frameworks such as LangGraph, CrewAI, or Semantic Kernel.
• Turn brittle, prompt-driven prototypes into reliable, code-based workflows backed by evaluation harnesses, guardrails, and measurable quality.
• Design schema-aware natural-language-to-SQL and other structured-data interfaces with query validation and safeguards.
• Own reliability in production: CI/CD, versioning, monitoring, observability, and rollback under real traffic.
• Integrate solutions with enterprise systems (ERP/MES/data warehouses) and downstream BI and collaboration tools.
• Set technical direction and raise the engineering bar through design reviews, code reviews, and mentorship.

Requirements

• Bachelor's or Master's degree in Computer Science, Data Science, AI Engineering, or a related quantitative field.
• 4+ years of professional software engineering experience, including software design, architecture, and shipping production-grade systems.
• Proven record of building and operating software or AI systems in production with real users.
• Strong programming ability in Python, with solid fundamentals in API design, testing, version control, and system design.
• Hands-on experience building applications with LLMs, including embeddings, retrieval-augmented generation (RAG), and evaluation.

Nice to Have

• Experience building agentic and multi-agent systems (LangGraph, CrewAI, AutoGen, or Semantic Kernel).
• Strong SQL and structured-data skills.
• Experience deploying and scaling on AWS, GCP, or Azure; Docker/Kubernetes, and managed AI hosting (SageMaker, Vertex AI, Azure ML).
• Familiarity with vector databases (Pinecone, Weaviate, Milvus, FAISS, or Chroma).
• Domain background in finance, supply chain, or manufacturing.

Skills

• Python
• LangGraph
• FastAPI
• RAG
• AWS