Senior AI/ML Engineer: Build Production-Ready Gen AI

Prodigy Resources; Denver (CO); On-site; USD 160,000 - 210,000; Full time

Job summary

Prodigy Resources in Denver seeks an experienced AI/ML Engineer to design, build, and deploy production-ready AI and ML solutions, including generative AI, LLM-powered apps, and intelligent automation. You will take AI capabilities from concept to production, develop RAG pipelines, embeddings, vector search, and orchestration, and build APIs and backend services for internal systems.

The role requires 5+ years of software/ML engineering, strong Python skills, and experience with AWS/Azure/GCP,

Qualifications

• 5+ years of professional software engineering or ML engineering experience.
• Strong programming skills in Python.
• Hands-on experience building and deploying AI/ML systems in production.
• Experience with LLMs and APIs from OpenAI, Anthropic, Google, or similar models.
• Experience with RAG, embeddings, vector databases, prompt engineering, and LLM evaluation.
• Understanding of APIs, microservices, distributed systems, and modern app architecture.
• Experience with ML/AI frameworks such as PyTorch, TensorFlow, Hugging Face, LangChain, LlamaIndex.
• Experience deploying AI/ML workloads on AWS, Azure, or GCP.
• Familiarity with Docker, CI/CD, Git, and MLOps practices.
• Experience with structured and unstructured data.
• Strong problem-solving skills and translating business problems into technical solutions.

Responsibilities

• Design, build, test, and deploy production-grade AI/ML applications and services.
• Develop apps using LLMs, generative AI, and modern ML techniques.
• Build RAG pipelines, AI agents, workflow automation, and intelligent search/retrieval solutions.
• Integrate commercial and open-source models into enterprise apps.
• Develop prompts, context management, embeddings, vector search, and model orchestration.
• Build APIs and backend services exposing AI/ML capabilities to apps and systems.
• Evaluate model and app performance for accuracy, reliability, latency, and cost.
• Design data pipelines supporting training, inference, retrieval, and evaluation.
• Implement guardrails, observability, and security controls for production AI.
• Collaborate with engineering, product, data, and business to identify high-value AI use cases.
• Prototype quickly with a clear path from PoC to scalable production.

Skills

Python

AI/ML systems in production

LLMs

RAG pipelines

Embeddings

Vector databases

Prompt engineering

APIs

Microservices

Distributed systems

PyTorch

TensorFlow

Hugging Face

LangChain

LlamaIndex

AWS

Azure

GCP

Docker

CI/CD

Git

DevOps/MLOps

Structured data

Unstructured data

Tools

PyTorch

TensorFlow

Hugging Face

LangChain

LlamaIndex

Docker

CI/CD

Git

Job description

Prodigy Resources in Denver seeks an experienced AI/ML Engineer to design, build, and deploy production-ready AI and ML solutions, including generative AI, LLM-powered apps, and intelligent automation. You will take AI capabilities from concept to production, develop RAG pipelines, embeddings, vector search, and orchestration, and build APIs and backend services for internal systems.

The role requires 5+ years of software/ML engineering, strong Python skills, and experience with AWS/Azure/GCP,