Lead AI/ML Engineer (Generative AI Agent Systems)

About the role

This Lead - AI/ML Engineer (Generative AI Agent Systems) role is based in India and operates remotely, serving as a senior technical authority for a partner company building production-grade Generative AI and autonomous agent systems for enterprise organizations. Day-to-day work combines hands-on engineering with consulting, architectural advisory, and technical delivery leadership, including defining reusable agent patterns, reference architectures, evaluation frameworks, and governance practices. You will work closely with senior client stakeholders to translate complex business challenges into secure, resilient, and measurable AI solutions within a cloud-native, distributed-systems environment.

What you’ll do

• Serve as the primary technical SME for Generative AI, LLM reasoning patterns, autonomous agents, and agentic workflows, advising enterprise clients and senior stakeholders on technical direction and s
• Translate complex business requirements into technical blueprints and architectural strategies, leading technical discovery sessions, solution assessments, and pre-sales engagements
• Establish playbooks, engineering patterns, and reusable frameworks that enable consistent and scalable deployment of agentic solutions across different clients and industries
• Define the technical vision for production-ready agent frameworks, including Go-based harness patterns and solutions leveraging the Vertex AI Agent Development Kit
• Establish detailed agent specifications covering function calling and tool definitions, prompt engineering, context and input data models, and operational behaviors
• Define graduated-autonomy models that balance autonomous execution with appropriate human-in-the-loop controls and exception handling
• Establish patterns for idempotency, event-driven communication, canonical event envelopes, and reliable interactions across bounded contexts
• Design continuous shadow-mode evaluation systems that assess agent performance against production-like data without creating real-world side effects

What you’ll bring

• 6–12 years of professional services, technology consulting, or similar experience leading technical delivery teams and working with senior client stakeholders such as CTOs and VPs of Architecture
• Deep, hands-on experience designing and deploying production-grade AI agent systems, multi-agent frameworks, LLM-backed reasoning loops, and autonomous workflows
• Expert knowledge of the Vertex AI ecosystem, including Agent Engine, Agent Development Kit, model tuning, and Vector Search, plus strong understanding of enterprise GCP security architectures
• Experience with VPC Service Controls, IAM, Pub/Sub, and secure cloud environments where strict security and compliance requirements apply
• Advanced proficiency in Go (Golang) with strong experience developing highly concurrent, distributed, and event-driven backend systems
• Strong understanding of agent design, tool/function calling, prompt engineering, context management, evaluation methodologies, and human-in-the-loop architectures
• Experience or strong understanding of AI safety, governance, observability, model version management, evaluation, and production monitoring
• Experience working with highly regulated industries such as healthcare, financial services, or the public sector where compliance, security, auditability, and controlled data access are critical

Skills

Benefits

• Remote work from India with a globally distributed team
• High-impact projects involving Generative AI, autonomous agents, cloud platforms, and emerging technologies
• Opportunity to shape AI architecture, engineering standards, reusable frameworks, and responsible AI practices at enterprise scale