Software Engineer

Prodigy Resources; Denver (CO); Remote; USD 180,000 - 240,000; Full time

Job summary

Prodigy Resources seeks a forward deployed engineer, AI, to embed with customer environments and build AI systems that run on messy data. The role is remote and US-based, sitting between the customer and product teams to scope problems and ship production code in Python.

You will deploy LLM apps, integrate with customer systems, evaluate performance and cost, and bring field learnings back to accelerate future deployments. 8+ years in software engineering and strong Python required.

Qualifications

• 8+ years in software engineering, with recent work shipping LLM-powered systems to production.

Responsibilities

• Scope AI use cases with customer teams and decide what to build.
• Build and deploy LLM applications: RAG pipelines, multi-step agents, and tool integrations over MCP.
• Connect models to customer systems: APIs, databases, data warehouses, SSO.
• Write evals, measure accuracy and cost, and fix production issues.
• Share learnings with the product team to speed up future deployments.

Skills

Python

TypeScript

LLM APIs

LangChain

LangGraph

LlamaIndex

MCP

OpenAI Agents SDK

Vector search

Cloud deployment

Customer-facing

Tools

pgvector

Pinecone

Weaviate

AWS

Azure

GCP

Bedrock

Azure OpenAI Service

Vertex AI

Job description

Forward deployed engineer, AI (remote)Our client puts engineers directly inside customer environments to build AI systems that work on messy, real data.

About the Role

You'll sit between the customer and the product team: scoping the problem, writing production code in Python, and getting it live. Remote, US-based.

Responsibilities

• Work with customer engineering and business teams to scope AI use cases and decide what's worth building.
• Build and deploy LLM applications: RAG pipelines, multi-step agents, and tool integrations over MCP.
• Connect models to the customer's systems: APIs, databases, data warehouses, SSO.
• Write evals, measure accuracy and cost, and fix what breaks in production.
• Bring what you learn in the field back to the product team so the next deployment goes faster.

Qualifications

• 8+ years in software engineering, with recent work shipping LLM-powered systems to production.

Required Skills

• Strong Python, plus TypeScript or another backend language.
• Hands-on work with LLM APIs from OpenAI, Anthropic (Claude), or Google (Gemini).
• Experience with LangChain, LangGraph, LlamaIndex, Model Context Protocol (MCP), or the OpenAI Agents SDK.
• Vector search with pgvector, Pinecone, or Weaviate.
• Cloud deployment on AWS, Azure, or GCP, including Bedrock, Azure OpenAI Service, or Vertex AI.
• You're comfortable in front of a customer's VP in the morning and in their codebase that afternoon.

Preferred Skills

• Daily use of Claude Code or Cursor.
• Agent-to-agent work using Google's A2A protocol.
• Prior consulting, solutions engineering, or customer-facing engineering roles.
• Experience with HIPAA or PII-regulated data.