Lead Engineer - AI

Job Description:

We are looking for a hands-on AI Lead Engineer who can lead both AI application development and AI platform engineering. The role will be responsible for building production-grade GenAI solutions and the cloud/platform capabilities required to deploy, scale, secure, and operate them across AWS and GCP.

The ideal candidate combines strong software engineering skills with practical experience in LLMs, RAG, AI agents, APIs, cloud, Kubernetes, and CI/CD.

A hands-on technical leader who can take an AI solution from prototype to development to production to operations, while establishing reusable platform capabilities that allow engineering teams to build and deploy AI solutions faster and more securely.

Responsibilities:

• Design and develop production-grade GenAI applications, APIs, RAG solutions, AI agents, and MCP-based services.
• Build reusable AI engineering patterns for LLM integration, prompt management, model routing, tool calling, evaluation, and guardrails.
• Proficiency in backend development using any of these languages - Go (Golang), Java, TypeScript, Node.js, and Python, including API development, database integration, and building scalable, high-performance backend services.
• Design and operate cloud-native AI workloads across AWS and GCP, using containers and Kubernetes.
• Build CI/CD pipelines for AI applications, models, agents, APIs, and supporting services, including automated deployment and rollback.
• Develop scalable AI platform capabilities for model serving, inference, artifact management, and agent/MCP deployment.
• Implement AI security and governance controls including authentication, authorization, secrets management, PII protection, prompt-injection protection, and data-leakage prevention.
• Build observability for AI workloads covering latency, errors, token usage, model performance, and cost.
• Work with data and application teams to integrate vector databases, RAG pipelines, enterprise APIs, and data platforms.
• Support API gateway and AI gateway capabilities including routing, rate limiting, authentication, retries, caching, and monitoring.
• Drive production reliability through scalability, high availability, disaster recovery, incident support, and operational best practices.
• Provide technical leadership, conduct architecture/design reviews, establish engineering standards, and mentor engineers.

Technical Skills Required:

• 7+ years of experience in software engineering, AI engineering, platform engineering, DevOps, or SRE.
• Strong hands-on development experience with Python and REST APIs/microservices.
• Production experience with Generative AI/LLMs, RAG, embeddings, AI agents, and model APIs.
• Strong experience with Docker, Kubernetes, Git, CI/CD, and Linux.
• Hands-on experience with AWS and/or GCP cloud services and cloud-native architectures.
• Experience including model packaging, deployment, versioning, artifact management, and monitoring.
• Experience with observability, logging, monitoring, troubleshooting, and production operations.
• Strong understanding of cloud security, IAM, secrets management, and service-to-service authentication.
• Experience working with vector databases and enterprise data integration.
• Strong communication and technical leadership skills.

Education & Experience:

• Experience with AWS EKS / GCP GKE or equivalent managed Kubernetes platforms.
• Experience with AI agents, MCP, agent orchestration, or AI gateway architectures.
• Experience with Databricks, Airflow, or similar platforms.
• Experience with Apigee, Kong, AWS API Gateway, or similar API gateway technologies.
• Experience with Partner with data, AI, security, and application teams to enable vector databases, graph databases, feature stores, and RAG pipelines as reusable platform services.
• Experience with AI security, evaluation, governance, and cost optimization.

Skills

AI Agents, AWS, CI / CD, Docker, Embeddings, GCP, Gen AI, Kubernetes, LLM, Python, RAG