AI Native Software Engineer (Agent Systems)- Remote within US

Position: AI Native Software Engineer (Agent Systems)

Location: Remote

Additional Requirement:

Hands-on experience building production-grade AI/LLM systems including agent-based workflows, RAG pipelines, orchestration frameworks, and multi-model integrations. Strong expertise in cloud-native architectures, observability, and performance optimization required.

Role Overview

We are seeking a highly skilled AI Native Software Engineer to design, build, and deploy enterprise-scale AI-driven systems. This is a fully hands-on engineering role focused on developing intelligent agent-based architectures, integrating AI platforms, and delivering scalable, production-ready cloud-native solutions.

The ideal candidate will have deep experience in building AI/LLM-powered systems, including retrieval-augmented generation (RAG), orchestration workflows, and multi-agent systems. This role requires strong backend engineering capabilities, expertise in cloud infrastructure, and the ability to optimize AI systems for performance, cost, and reliability.

You will work closely with internal and client engineering teams to implement robust AI applications aligned with business workflows, while ensuring production readiness through monitoring, testing, and continuous improvement.

Key Responsibilities

AI Agent Engineering

• Design and implement AI agents including RAG pipelines, orchestration workflows, tool/function invocation, and policy-based routing

• Build evaluation frameworks to measure accuracy, latency, and reliability of AI systems

• Implement observability, monitoring, and lifecycle management for AI agents

AI Platform Integration

• Integrate with AI providers such as OpenAI, Anthropic, Vertex AI, and open-source models

• Develop abstraction layers to enable multi-model and multi-provider architectures

• Optimize model usage for performance, latency, and cost efficiency

Cloud-Native Development

• Develop scalable microservices-based systems using containers (Docker, Kubernetes)

• Implement serverless and event-driven architectures

• Build and maintain CI/CD pipelines and infrastructure as code using tools like Terraform and Helm

• Ensure production readiness with logging, monitoring, and fault-tolerant design

Application Development

• Build and deploy AI-powered applications aligned with enterprise business workflows

• Integrate AI systems with existing platforms, services, and APIs

• Develop backend services and APIs supporting agent-based systems

Testing & Performance Optimization

• Define and execute testing strategies for AI systems

• Measure and monitor system performance including latency, throughput, accuracy, and cost

• Debug, troubleshoot, and optimize production systems

Required Qualifications

• Bachelor’s degree in Computer Science, Engineering, or related field (or equivalent experience)

• 8–10+ years of software engineering experience

• Strong experience with cloud-native systems including APIs, microservices, containers, and serverless architectures

• Proven experience building and deploying AI/LLM-based systems in production (agents, RAG, orchestration)

• Proficiency in Python, Java, or similar backend languages

• Hands-on experience with CI/CD pipelines and infrastructure as code

• Experience with monitoring and observability tools

• Practical experience integrating AI platforms such as OpenAI, Claude, Vertex AI, or similar

Preferred Qualifications

• Experience with agent frameworks such as LangGraph, AutoGen, or CrewAI

• Experience designing multi-agent or distributed AI systems

• Familiarity with enterprise-scale system integration

• Experience optimizing AI workloads for performance and cost efficiency

Scope & Expectations

• 100% hands-on engineering role (no people management responsibilities)

• Deliver high-quality, production-ready code and deployments

• Work within established architecture and engineering standards

• Collaborate effectively with internal and client engineering teams

• Actively participate in technical design discussions with a focus on implementation