Senior Gen AI Cloud Engineer

JSR Tech Consulting; Newark (NJ); On-site; USD 150,000 - 190,000; Full time

Job summary

JSR Tech Consulting is seeking a Senior GenAI Cloud Engineer in Newark, NJ to build and deploy enterprise-scale AI solutions, including agents, chatbots, and RAG applications. You will design, develop, and deliver production-grade AI apps using modern cloud architectures and LLMs, while mentoring engineers and shaping standards.

You will lead workstreams end-to-end, integrate AI capabilities with enterprise systems, and ensure security, observability, and reliability across deployments.

Qualifications

• 5–8 years of software engineering experience.
• Experience developing Microservices, APIs, and distributed applications.
• Hands-on experience with AWS cloud services and cloud-native application development.
• Recent experience building enterprise GenAI solutions, including AI agents, chatbots, or RAG applications.
• Experience with AWS Bedrock or other enterprise LLM platforms.
• Experience with data ingestion, vector databases, embeddings, and semantic search.
• Experience implementing AI guardrails, safety controls, intent classification, and routing logic.
• Strong understanding of software engineering best practices, application security, scalability, and production operations.
• Experience mentoring engineers and leading delivery of a technical workstream.

Responsibilities

• Build and deploy enterprise AI agents, chatbots, and GenAI-powered applications.
• Implement data ingestion, document processing, embedding generation, vectorization, and retrieval pipelines.
• Develop intent classification, orchestration, guardrail, and safety capabilities for AI applications.
• Integrate LLMs with enterprise systems, APIs, databases, and business workflows.
• Contribute to system design, testing, deployment, monitoring, and operational support.
• Uphold code quality, security, and observability standards in everything you ship.
• Stay current with emerging AI technologies, frameworks, and platform capabilities.
• Lead a workstream: Take technical ownership of a defined feature area or service - from design through production support - coordinating a small group of engineers where needed.
• Mentor engineers: Guide associate and mid-level engineers through code review, pairing, and design feedback; help them build GenAI and cloud skills.
• Contribute to architecture: Participate actively in design reviews, propose solution options with clear trade-offs, and help shape the patterns and standards the team adopts.
• Influence through delivery: Partner directly with product owners, architects, and business stakeholders to refine requirements and build credibility through working software.
• Improve the team: Identify and drive improvements in engineering practices, tooling, reusable components, and documentation; share knowledge through demos and internal write-ups.

Skills

Microservices development

APIs & distributed apps

GenAI solutions

Mentoring engineers

Architecture reviews

Security & observability

Tools

AWS Bedrock

LangGraph

LangChain

AWS AgentCore

Vector databases

Serverless AWS

Job description

Our client is seeking a Senior GenAI Cloud Engineer to build and deploy enterprise-scale AI solutions that drive intelligent automation, conversational experiences, and business process transformation. This is a Right-to-Hire Opportunity.

This is a hands-on engineering role responsible for designing, developing, and delivering production-grade AI applications using modern cloud architectures, large language models, and agentic AI frameworks. You will lead the implementation of specific workstreams end to end, mentor less experienced engineers, and contribute to the architecture and standards used by many engineering teams. The ideal candidate has recent experience building AI agents, chatbots, and RAG-based solutions in enterprise environments.

KEY RESPONSIBILITIES

• Build and deploy enterprise AI agents, chatbots, and GenAI-powered applications.
• Implement data ingestion, document processing, embedding generation, vectorization, and retrieval pipelines.
• Develop intent classification, orchestration, guardrail, and safety capabilities for AI applications.
• Integrate LLMs with enterprise systems, APIs, databases, and business workflows.
• Contribute to system design, testing, deployment, monitoring, and operational support.
• Uphold code quality, security, and observability standards in everything you ship.
• Stay current with emerging AI technologies, frameworks, and platform capabilities.

LEADERSHIP, MENTORING & INFLUENCE

• Lead a workstream: Take technical ownership of a defined feature area or service - from design through production support - coordinating a small group of engineers where needed.
• Mentor engineers: Guide associate and mid-level engineers through code review, pairing, and design feedback; help them build GenAI and cloud skills.
• Contribute to architecture: Participate actively in design reviews, propose solution options with clear trade-offs, and help shape the patterns and standards the team adopts.
• Influence through delivery: Partner directly with product owners, architects, and business stakeholders to refine requirements and build credibility through working software.
• Improve the team: Identify and drive improvements in engineering practices, tooling, reusable components, and documentation; share knowledge through demos and internal write-ups.

REQUIRED QUALIFICATIONS:

• 5–8 years of software engineering experience.
• Experience developing Microservices, APIs, and distributed applications.
• Hands-on experience with AWS cloud services and cloud-native application development.
• Recent experience building enterprise GenAI solutions, including AI agents, chatbots, or RAG applications.
• Experience with AWS Bedrock or other enterprise LLM platforms.
• Experience with data ingestion, vector databases, embeddings, and semantic search.
• Experience implementing AI guardrails, safety controls, intent classification, and routing logic.
• Strong understanding of software engineering best practices, application security, scalability, and production operations.
• Experience mentoring engineers and leading delivery of a technical workstream.

PREFERRED QUALIFICATIONS

• Experience with AWS AgentCore.
• Experience with LangGraph, LangChain, or similar agent frameworks.
• Experience with model tuning, evaluation, and prompt engineering.
• Experience with event-driven architectures and AWS serverless technologies.
• Experience delivering solutions in financial services, insurance, or other regulated industries.