PRX- AI Engineer

Infostretch Corporation
Hope, United States of America
2 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Intermediate

Job location

Hope, United States of America

Tech stack

Java
Artificial Intelligence
Amazon Web Services (AWS)
Amazon Web Services (AWS)
C++
Cloud Computing
Data Structures
Amazon DynamoDB
Python
Machine Learning
Software Engineering
Large Language Models
State Machines
Caching
Cloudformation
Machine Learning Operations
Functional Programming
Terraform
Redshift
Go

Job description

Experteer Overview In this role you will design and deploy agentic AI solutions to reduce risk and cost in large-scale production environments. You will work with production engineers and application teams to translate pain points into AI roadmaps, building tools that diagnose, reason, and act automatically. You will establish safety, governance, and performance guardrails while optimizing for reliability and cost. This position offers impact through integrating AI agents with observability, incident management, and deployment systems, supporting auditable, business-aligned outcomes. You will mentor peers and drive engineering excellence in agent architectures and deployment practices. Compensation / Benefits * Design and implement tool-calling agents with retrieval, structured reasoning, and secure action execution (MCP protocol) * Productionize LLMs by building evaluation frameworks, retrieval/prompt pipelines, and self-correction loops * Integrate agents with observability, incident management, and deployment systems for automated diagnostics and remediation * Collaborate with production engineers and application teams to translate pain points into agentic AI roadmaps and measurable outcomes * Build safety, reliability, and governance features including validator models, adversarial prompts, and fallback strategies * Optimize cost and latency via prompt engineering, context management, caching, routing, batching, and parallel tool-calls * Build a RAG pipeline with domain knowledge, data-quality validation, and knowledge freshness feedback loops * Drive design reviews and high-quality engineering practices; mentor peers on agent architectures and safe deployment patterns Tasks * 5+ years of software development experience in Python, C/C++, Go, or Java (preferably Python) * 3+ years designing, architecting, and deploying production ML systems * Hands-on experience with Large Language Models (LLMs), API integration, and tool-using agents (vector retrieval, function calling) * Understanding of multiple LLMs (OpenAI, Gemini, Llama, Qwen, Claude) * Strong foundation in applied statistics, ML concepts, and data structures * Strong analytical problem-solving, ownership, urgency, and ability to collaborate across global teams * Preferred: experience with cloud infrastructure (AWS), ECS/EKS, Lambda, S3, DynamoDB, Redshift, Step Functions, SageMaker, Terraform/CloudFormation Key requirements * Health Insurance with Dental & Vision * 401K Plan * Life Insurance, STD & LTD * Paid Vacations & Holidays * Paid Parental Leave * FSA Dependent & Limited Purpose care

Requirements

practices. and deployment systems for automated diagnostics and remediation * Collaborate with production engineers and application teams to translate pain points into agentic AI roadmaps and measurable outcomes * Build safety, reliability, and governance features including validator models, adversarial prompts, and fallback strategies * Optimize cost and latency via prompt engineering, context management, caching, routing, batching, and parallel tool-calls * Build a RAG pipeline with domain knowledge, data-quality validation, and knowledge freshness feedback loops * Drive design reviews and high-quality engineering practices; mentor peers on agent architectures and safe deployment patterns Tasks * 5+ years of software development experience in Python, C/C++, Go, or Java (preferably Python) * 3+ years designing, architecting, and deploying production ML systems * Hands-on experience with Large Language Models (LLMs), API integration, and tool-using agents (vector retrieval, function aaaaaaA _ * Understanding of multiple LLMs (OpenAI, Gemini, Llama, Qwen, Claude) * Strong foundation in applied statistics, ML concepts, and data structures * Strong analytical problem-solving, ownership, urgency, and ability to collaborate across global teams * Preferred: experience with cloud infrastructure (AWS), ECS/EKS, Lambda, S3, DynamoDB, Redshift, Step Functions, SageMaker, Terraform/CloudFormation Key requirements * Health Insurance with Dental & Vision * 401K Plan * Life Insurance, STD & LTD * Paid Vacations & Holidays * Paid Parental Leave * FSA Dependent & Limited Purpose care

Apply for this position