AI Engineer Lead

JPS Tech Solutions Pvt Ltd; New York, Northern (NY, KY); Hybrid; USD 180,000 - 260,000; Full time

Job summary

JPS Tech Solutions Pvt Ltd is seeking a Lead AI Engineer to helm enterprise AI platforms, focusing on agentic AI, Claude Code harnesses, and robust governance. You will guide architecture, security, and reliability across AI ecosystems.

The role demands deep experience in AI engineering and hands-on leadership to design scalable, secure AI workflows and automation for complex enterprise environments.

Qualifications

• 12+ years of IT/software engineering experience.
• Strong hands-on expertise in Artificial Intelligence and Commercial Generative AI.
• Experience designing AI agent ecosystems and AI orchestration workflows.
• Experience with AI security, governance and compliance in enterprise settings.
• Ability to create reusable AI engineering patterns and templates.

Responsibilities

• Design and build AI agent and skills execution environments for enterprise applications.
• Build and harden Claude Code harnesses, skills, templates, and agent execution workflows.
• Develop validation and automation pipelines for AI agents and solutions.
• Implement policy enforcement, security controls, and governance gates across AI workflows.
• Establish observability, auditability, and reliability for AI systems.
• Provide technical leadership for AI architecture and AI-embedded platforms.
• Collaborate with engineering, data, security, and business teams to deliver production-ready AI solutions.

Skills

AI engineering

Generative AI

Agentic AI

Claude Code

Technical architecture

Automation

Security controls

Observability

Reliability engineering

Enterprise governance

SaaS modernization

AI orchestration

Tools

Claude Code harnesses

Job description

Job Description:

We are seeking a highly experienced Lead AI Engineer with strong expertise in Artificial Intelligence, Commercial Generative AI, Agentic AI, and Claude Code. The ideal candidate will have a multidisciplinary background spanning software engineering, data, infrastructure, AI architecture, and automation.

The candidate will be responsible for designing, building, securing, and governing AI agent ecosystems and execution environments, while establishing technical standards, validation frameworks, security controls, observability, and reliability mechanisms for enterprise AI platforms.

Key Responsibilities

• Design and build AI agent and skills execution environments for enterprise applications.
• Build and harden Claude Code harnesses, skills, templates, and agent execution workflows.
• Develop validation and automated testing pipelines for AI agents and AI-enabled solutions.
• Implement policy enforcement, security controls, and compliance gates across AI workflows.
• Build feedback loops and mechanisms to support self-healing AI workflows.
• Develop and manage benchmarks, golden datasets, and evaluation frameworks.
• Establish strong auditability, observability, monitoring, and reliability for AI systems.
• Design and implement specialized AI agents based on business and technical requirements.
• Provide technical leadership for domain-level AI architecture and AI-embedded platforms.
• Create solution architecture, technical design documents, standards, and reusable AI engineering patterns.
• Support Greenfield, Brownfield, legacy modernization, and SaaS conversion programs.
• Collaborate with engineering, infrastructure, data, security, and business teams to deliver production-ready AI solutions.

Required Qualifications

• 12+ years of overall IT/software engineering experience.
• Strong hands-on expertise in Artificial Intelligence and Commercial Generative AI.
• Strong experience with Claude Code, including building and hardening AI harnesses.
• Experience designing and implementing Agentic AI systems and AI orchestration workflows.
• Strong understanding of AI engineering, automation, infrastructure, data, and software development.
• Experience building AI validation, testing, evaluation, and governance frameworks.
• Experience with AI security, compliance, policy enforcement, and enterprise governance.
• Strong experience with observability, auditability, reliability, and performance optimization for AI systems.
• Experience working on legacy, Brownfield, Greenfield, SaaS, and regulatory projects.
• Strong ability to create solution designs, technical designs, AI skills, templates, and reusable engineering frameworks.

Core Expertise

• End-to-end conversational-to-production AI workflows
• AI agent and skills development
• Claude Code harness development and hardening
• AI testing and automation
• Agent validation and evaluation
• AI security and compliance
• Policy enforcement and governance
• Golden datasets and benchmarking
• AI observability and auditability
• Greenfield / Brownfield modernization
• SaaS conversion programs
• Technical architecture and solution design