Principal Engineer - AI Engineering
MontyCloud20 days ago
Bengaluru, IndiaStaff+
Responsibilities
- Define and own the technical vision for agentic AI systems across the platform.
- Architect multi-agent systems, orchestration frameworks, MCP server infrastructure, retrieval and memory pipelines, and observability layers.
- Design and develop critical AI platform components and infrastructure for enterprise-scale cloud operations.
- Establish AI engineering practices covering design patterns, evaluation, prompt engineering, reliability, governance, and cost optimization.
- Lead cross-functional technical initiatives and influence architecture, engineering, and product roadmaps.
- Mentor Lead and Staff AI Engineers through architecture reviews, design discussions, and technical problem-solving.
- Conduct rigorous reviews of system designs, architectures, and major code contributions.
- Develop prototypes, technical proposals, and proofs of concept for new agentic AI capabilities.
- Contribute to technical writing, open-source projects, conference talks, or other technical community activities.
Requirements
- 12+ years of overall software engineering experience.
- Prior experience as a Principal Engineer or equivalent individual-contributor technical leader.
- Significant recent hands-on experience building and deploying applied AI systems in production.
- Production-grade experience designing and developing agentic AI and multi-agent systems.
- Experience with agent orchestration, agent-to-agent communication, memory and planning strategies, tool integration, and MCP server design.
- Experience with AI governance, prompt versioning, evaluation frameworks, regression detection, observability, tracing, and AI cost management.
- Experience with AWS cloud services, AWS Bedrock, AgentCore, Kubernetes, Docker, and Terraform.
- Experience integrating foundation model APIs such as OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, and Hugging Face.
- Experience with RAG, Graph-RAG, embeddings, retrieval and reranking systems, and knowledge graph integrations.
- Proven record of leading large-scale technical initiatives across multiple teams or product areas.
- Demonstrated expertise architecting enterprise-scale AI platforms and cloud-native AI workloads.
- Experience mentoring senior engineers and influencing organization-level technical strategy.
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Engineering, or a related technical discipline, or equivalent practical experience.
- Preferred qualifications include cloud operations or infrastructure automation experience, developer tooling experience, serverless AI deployment, inference cost optimization, model fine-tuning, RLHF, advanced model evaluation, and AI community or open-source experience.