Junior Software Engineer (Backend + AI)

1w1 week ago

Newton Research

US · Full-time · $90,000 – $110,000

About this role

Newton Research builds an AI-powered research and analysis platform used by enterprises to unlock insights from their data. The platform connects to major data warehouses like BigQuery, Snowflake, Databricks, and Redshift, runs autonomous AI agents over structured and unstructured data, and presents findings through a rich interactive frontend. We're a small, high-output team where interns work on production code from week one.

You'll touch production code in a codebase with 7,700+ lines of Django models, complex multi-table relationships, and AI agent pipelines that call LLMs, execute tools, and reason over enterprise data. Typical work includes building API endpoints with DRF serializers and viewsets, extending LangGraph-based AI agents, and writing RQ async task workers for document parsing and LLM inference.

Our stack includes Python 3.13, Django 5.2, PostgreSQL, Redis on the backend; OpenAI, Anthropic, LangChain for AI/ML; React 19, TypeScript on frontend; and Docker, AWS, pytest for infra and testing. You'll improve test coverage with pytest, ship React components with TanStack Query, and debug AI hallucinations in retrieval pipelines.

This role builds backend fundamentals while exploring AI agent capabilities and frontend features in a real production environment. You'll learn data modeling with JSONFields and custom managers, semantic search with vector embeddings, and diagnosing irrelevant AI results.

Requirements

Solid Python fundamentals: write a class, debug a traceback, reason about data structures without AI autocomplete
Familiarity with web APIs: understand HTTP methods, JSON serialization, request/response cycles
Comfort with Git: branching, rebasing, resolving merge conflicts
Experience with at least one database: SQL queries, basic schema design
Genuine curiosity about AI/ML: used LLM APIs, built a RAG pipeline, fine-tuned a model, or experimented beyond ChatGPT
Ability to debug AI-generated code: we use AI tools extensively but shipping broken output is unacceptable
Django or Flask experience
React/TypeScript experience

Responsibilities

Build API endpoints with DRF serializers and viewsets that serve data to React frontend
Extend AI agent capabilities by adding new tools to LangGraph-based agents and working on RAG memory systems with vector embeddings
Write async task workers using RQ for document parsing (PDF/Excel/PowerPoint) and LLM inference pipelines
Improve test coverage with pytest tests, database fixtures, mocked APIs, and N+1 query detection
Ship frontend features building React components with TypeScript, TanStack Query, and SCSS Modules
Debug AI output including agent hallucinations and irrelevant retrieval results in pipelines