We are seeking a Technology Architect / Senior AI Engineer – Applied AI to drive the design and implementation of enterprise-grade Agentic AI solutions for a global organization.
The ideal candidate will have strong hands-on experience designing agentic AI architectures, multi-agent workflows, memory systems, retrieval infrastructure, and production-grade AI applications .
You will work closely with product, engineering, data, security, risk, and compliance teams to build scalable, secure, reliable, and governable AI agent ecosystems.
Top 3 Skills Required
- Stateful orchestration and state machines
- Short-term and long-term memory architectures
- Episodic memory/summarization
- Retry and self-correction mechanisms
2. Data & Retrieval Infrastructure
- Vector and relational databases
- Semantic/vector similarity search
- Metadata management
- Data ingestion, processing, storage, and retrieval
3. Production Reliability & Performance
- End-to-end tracing and observability
- Debugging non-deterministic agent behavior
- Token/cost tracking
- Automated AI evaluation frameworks
- High-performance asynchronous Python
- Fault tolerance and scalable AI API integrations
Key Responsibilities
- Design end-to-end Agentic AI architectures supporting scalable enterprise solutions across multiple business domains.
- Architect modular AI agent frameworks with reusable components, orchestration workflows, and interoperability with enterprise systems.
- Design stateful, cyclic, multi-agent workflows and state machines for production environments.
- Develop AI agent lifecycle strategies covering agent creation, validation, deployment, monitoring, iteration, and retirement.
- Design multi-layered memory architectures including short-term, long-term, and episodic memory.
- Design reliable tool/function-calling frameworks with retry, error handling, and self-correction capabilities.
- Define AI agent data infrastructure covering data ingestion, processing, storage, metadata, and secure access patterns.
- Architect hybrid RAG solutions combining relational/exact-match retrieval with vector-based semantic search.
- Design solutions using relational databases, vector databases, and document stores for agent state and execution data.
- Establish AI governance frameworks, guardrails, security controls, compliance standards, and accountability mechanisms.
- Implement observability and tracing to monitor agent execution, identify loops/failures, and track performance and token consumption.
- Develop automated evaluation frameworks to measure agent quality, accuracy, reliability, and performance before production deployment.
- Provide technical leadership around Python-based backend development , including clean, concurrent, and asynchronous code.
- Collaborate with product, engineering, operations, security, risk, and compliance teams.
- Review existing AI agent implementations and identify architectural gaps, scalability issues, and opportunities for improvement.
- Define architecture standards, reference architectures, design patterns, and technical documentation.
- Provide guidance on performance optimization, fault tolerance, scalability, maintainability, and production readiness.
- Mentor engineering teams on Agentic AI architecture, agent engineering, data infrastructure, and responsible AI practices .
- Evaluate emerging Agentic AI frameworks, technologies, and methodologies and translate them into practical enterprise solutions.
Required Qualifications
- 10–14+ years of software engineering, architecture, AI/ML, or related technology experience.
- Strong hands-on experience designing and implementing Agentic AI solutions .
- Experience with AI agent frameworks and agent engineering patterns .
- Strong understanding of:
- Multi-agent orchestration
- Agent memory
- Tool/function calling
- RAG
- Vector search
- Embeddings
- Strong knowledge of relational, vector, and document-oriented data stores.
- Experience with event-driven architectures and data pipelines.
- Strong Python development skills, preferably including asynchronous/concurrent programming .
- Experience with AI observability, tracing, evaluation, monitoring, and production troubleshooting.
- Understanding of AI governance, security, compliance, responsible AI, and enterprise risk management.
- Strong architecture, design, troubleshooting, communication, and mentoring skills.
Preferred Qualifications
- Experience with enterprise LLM/GenAI platforms and APIs .
- Experience building production-grade RAG and agentic applications.
- Experience with vector databases and semantic search technologies.
- Experience with AI evaluation/evals frameworks.
- Experience with cloud platforms and hybrid enterprise environments.
- Experience with AI governance and responsible AI frameworks.
- TOGAF AI specialization or equivalent AI/ML/AI Engineering certification is preferred.