AI Engineer

TekCommands Inc; Michigan; Remote; USD 150,000 - 210,000; Full time

Job summary

TekCommands Inc. seeks an AI Engineer to design and scale LLM-powered applications remotely, building multi-agent workflows and robust AI systems.

You will implement RAG pipelines, optimize inference costs, and ensure reliable production with LLMOps. Strong Python skills and backend API experience are required, along with hands-on work with PyTorch, HuggingFace, LangChain, LangGraph and cloud platforms.

Qualifications

• 12+ years of experience in AI/ML engineering.
• Bachelor's degree in Computer Science or related field.
• Experience with LLMs, RAG, and AI pipelines.

Responsibilities

• Architect Systems: Design LLM-powered applications and scalable multi-agent workflows.
• Implement RAG: Build Retrieval-Augmented Generation pipelines using vector databases and semantic search.
• Optimize Performance: Fine-tune prompts, manage inference costs, and reduce latency.
• Ensure Reliability: Implement safety guardrails, output validation, and LLMOps monitoring in production.
• Collaborate: Translate business requirements into technical AI solutions with cross-functional teams.
• Programming: Strong proficiency in Python and backend API integrations.
• AI Frameworks: PyTorch, HuggingFace, LangChain, or LangGraph.
• Cloud & Tools: AWS, GCP, Azure, Docker.

Skills

Python

Backend API integrations

Education

Bachelor's degree in Computer Science or related field

Tools

Docker

AWS

GCP

Azure

PyTorch

HuggingFace

LangChain

LangGraph

Job description

AI Engineer

Role is remote

GCP experience needed

Years of experience required: 12+

Education: A bachelor's degree in Computer Science or a related technical field, or equivalent practical software development experience.

Key Responsibilities

• Architect Systems: Design LLM-powered applications and scalable multi-agent workflows.
• Implement RAG: Build Retrieval-Augmented Generation pipelines using vector databases and semantic search.
• Optimize Performance: Fine-tune prompts, manage inference costs, and reduce latency.
• Ensure Reliability: Implement safety guardrails, output validation, and LLMOps monitoring in production.
• Collaborate: Translate business requirements into technical AI solutions with cross-functional teams.
• Programming: Strong proficiency in Python and backend API integrations.
• AI Frameworks: Extensive experience with any of the tools like PyTorch, HuggingFace, LangChain, or LangGraph.
• Cloud & Tools: Exposure to cloud platforms (AWS, GCP, or Azure) and containerization tools like Docker.