About the role

Enterprise AI Architect

Department: AI Solutions

Location: Hybrid / Remote

Experience: 5+ years

ABOUT THE ROLE

We are looking for an Agentic AI Engineer to design, build, execute, test, and orchestrate autonomous AI agent systems that operate across complex, multi-step workflows. You will work at the intersection of large language models, tool-use frameworks, and enterprise data pipelines to deliver reliable, production-grade agentic solutions.

LLM Orchestration
Agent Design
Tool Use
Prompt Engineering
Multi-agent Systems

KEY RESPONSIBILITIES

Design and implement agentic AI systems (single-agent and multi-agent) with tool usage, memory management, and fallback mechanisms.
Build production-grade AI agents using frameworks such as LangGraph, AutoGen, CrewAI, or custom LLM orchestration layers.
Implement agent reasoning loops including planning, tool selection, execution, observation, reflection, and re-planning with safety guardrails.
Develop prompt engineering and context engineering strategies for reliable, grounded, and enterprise-ready LLM outputs.
Design agent orchestration workflows including task routing, parallel execution, retries, state management, and human-in-the-loop escalation.
Build evaluation frameworks for LLMs and AI agents including automated testing, adversarial testing, hallucination detection, and performance benchmarking.
Implement retrieval and grounding architectures using vector databases, embeddings, semantic search, and knowledge graphs for contextual accuracy.
Design scalable memory, caching, and context management layers to optimize token consumption, latency, and performance.
Ensure observability of AI agent systems by tracing LLM calls, tool usage, prompts, token utilization, and decision paths using monitoring frameworks.
Apply enterprise AI security and governance controls including prompt injection defense, access control, secure tool execution, and responsible AI practices.
Optimize AI agent systems for scalability, reliability, latency, throughput, and production cost efficiency.
Build CI/CD and MLOps pipelines for AI agent workflows including versioning, automated testing, deployment, and rollback strategies.
Integrate AI agents with enterprise systems, APIs, databases, and cloud platforms to automate end-to-end business workflows.
Design continuous feedback and learning loops using production traces, telemetry, and evaluation signals to improve AI agent quality and performance.
Experience with Model Context Protocol (MCP) systems to design database connections, integrate APIs, and enable secure tool orchestration for AI agents.
Hands-on experience in fine-tuning LLMs for domain-specific applications using LoRA, PEFT, QLoRA, RLHF, instruction tuning, and other parameter-efficient adaptation techniques.
Collaborate with data governance, architecture, security, and engineering teams to establish enterprise AI standards and best practices.
Stay current with emerging agentic AI frameworks, LLM research, semantic AI technologies, and enterprise AI deployment best practices.
Define infrastructure, networking, storage, compute, and deployment architectures for cloud and hybrid environments.
Collaborate with application, data, AI, security, and infrastructure teams to establish enterprise architecture standards and roadmaps.
Provide technical leadership, architecture reviews, solution guidance, and best practices across engineering teams.
Support AI/ML and Agentic AI platform integration with enterprise applications, data platforms, APIs, and cloud infrastructure.
Optimize enterprise systems for performance, reliability, latency, observability, and operational efficiency.
Architect microservices, event-driven systems, distributed computing, and API-based integration solutions.

REQUIRED SKILLS & EXPERIENCE

Minimum 5+ years of AI engineering experience, including 3+ years working with LLMs, Generative AI, and agentic AI systems in production.
Hands-on experience designing agentic AI architectures including ReAct, plan-and-execute, reflection loops, multi-agent orchestration, and tool-use patterns.
Strong proficiency in Python and experience with frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or Semantic Kernel.
Strong understanding of prompt engineering, context engineering, structured outputs, and grounding strategies for enterprise AI applications.
Experience building AI integrations with REST APIs, databases, vector stores, SQL executors, and enterprise applications.
Hands-on experience with RAG architectures, embeddings, vector databases, semantic search, and knowledge graphs.
Familiarity with LLM evaluation frameworks including RAGAS, adversarial testing, hallucination detection, and LLM-as-a-judge patterns.
Strong understanding of AI security and governance including prompt injection defense, secure tool execution, access control, and responsible AI practices.
Experience with MLOps and observability tools such as MLflow and Weights & Biases.
Strong experience designing memory, caching, and context management layers for scalable agentic AI systems with token cost optimization strategies.
Hands-on experience with LLM fine-tuning using LoRA, PEFT, QLoRA, RLHF, and instruction tuning techniques.
Experience with MCP systems for secure tool orchestration, API integration, and enterprise connectivity.
Strong experience in enterprise system architecture, distributed systems, cloud platforms, microservices, API integrations, and scalable application design.
Hands-on expertise with cloud and DevOps technologies including Amazon Web Services, Microsoft Azure, Google Cloud, Docker, Kubernetes, CI/CD, monitoring, and observability frameworks.
Strong understanding of security architecture, high availability, performance optimization, disaster recovery, and enterprise integration patterns for modern AI and data-driven platforms.

NICE TO HAVE

Experience with multi-agent systems and inter-agent communication protocols.
Exposure to data lineage, metadata management, or data catalog systems.
Contributions to open-source agentic AI projects.
Hands-on experience with Java, Scala, PySpark, and COBOL development.

WHAT WE OFFER

Opportunity to build frontier agentic AI systems on real enterprise data.
Collaborative environment with data engineers, AI researchers, and product teams.
Competitive salary and flexible working arrangements.