Agentic AI Engineer

Agentic AI Engineer

About the Opportunity

We're partnering with a globally recognized enterprise organization that is

making a significant investment in next-generation AI capabilities and building a world-class AI Engineering function.

This team is focused on developing intelligent systems that combine

cutting-edge AI research with large-scale enterprise deployment, tackling some of the most challenging problems in reasoning, orchestration, retrieval, memory management, and autonomous workflow execution.

As an Agentic AI Engineer, you'll play a key role in designing and building production-grade AI systems capable of reasoning, planning, retrieving information, using tools, and executing complex workflows at scale. You'll work alongside AI researchers, platform engineers, architects, and product leaders to help define how intelligent systems operate within real-world enterprise environments.

This is not a prompt-engineering-only role. We are looking for engineers who think deeply about system behavior, context management, grounding, reliability, and how intelligent agents perform under real-world operational constraints.

Work You'll Do

As an Agentic AI Engineer, you will design, build, and operationalize LLM-powered systems capable of reasoning, planning, retrieving information, using tools, and executing multi-step workflows reliably at scale.

You will work on the "thinking layer" of modern AI systems, including:

Agent architecture and orchestration
Tool integration and workflow execution
Retrieval and grounding pipelines
Memory and context management
Evaluation and observability
Reliability, safety, and guardrails

You will help shape how complex domain knowledge is transformed into production-grade AI behavior, with a strong emphasis on precision, traceability, maintainability, and operational robustness.

Key Responsibilities

Design and implement agentic AI systems capable of multi-step reasoning, planning, tool use, and workflow execution.
Build stateful workflows using frameworks such as LangGraph and LangChain, including branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns.
Develop and integrate Retrieval-Augmented Generation (RAG) pipelines, including ingestion, chunking, embeddings, vector and hybrid retrieval, reranking, contextual compression, and grounding strategies.
Engineer memory and context management capabilities, including conversational state, persistent memory, retrieval-aware context assembly, and token-efficient context engineering.
Build integrations with internal and external tools, APIs, enterprise systems, databases, and model providers so agents can operate safely within real business workflows.
Contribute to context delivery and model interaction patterns that improve how AI systems discover, retrieve, and use relevant information.
Evaluate system quality across both retrieval and generation layers using automated metrics, human review, and task-based evaluation frameworks.
Implement observability for prompts, tool calls, retrieval quality, agent traces, failures, drift, latency, and production behaviour.
Apply guardrails, safety controls, and failure handling mechanisms to improve reliability and reduce hallucinations or unsafe actions.
Stay current on advances in LLMs, agentic systems, evaluation methodologies, and context engineering, translating research and emerging techniques into practical engineering decisions.

Required Qualifications

Bachelor's degree in Computer Science, Engineering, Data Science, Computational Linguistics, or a related field.
Hands-on experience building production-grade applications with LLMs, including prompt engineering, tool use, structured outputs, error handling, and model behaviour tuning.
Strong experience with LangChain and especially LangGraph for orchestrating complex LLM workflows and agent behaviour.
Experience designing and optimizing end-to-end RAG systems, including indexing, retrieval, reranking, grounding, and evaluation.
Strong understanding of memory and context management, including context windows, retrieval-driven context assembly, persistent memory, and high-signal context selection.
Deep understanding of LLM behaviour in practice, including strengths, limitations, hallucination risks, reasoning constraints, latency/cost trade-offs, and evaluation methods.
Strong Python engineering skills and familiarity with modern software engineering practices, including testing, CI/CD, version control, and API integration.
Experience implementing observability, tracing, and debugging for LLM-based systems in production.
Ability to translate ambiguous, high-complexity business processes into robust system logic and reusable AI patterns.

Preferred Qualifications

Experience with multi-agent systems and agent collaboration patterns.
Familiarity with vector databases and retrieval infrastructure such as Pinecone, Weaviate, or Milvus.
Exposure to model adaptation and fine-tuning techniques such as LoRA or QLoRA.
Understanding of traditional NLP concepts including tokenization, semantic similarity, entity extraction, summarization, and transformer fundamentals.
Demonstrated habit of staying current with AI research, benchmarks, and emerging engineering patterns.
Experience operating in highly regulated, high-stakes, or operationally complex enterprise environments.

The Team

You will join a multidisciplinary team of AI engineers, platform architects, researchers, and technical leaders building the next generation of enterprise AI systems.

The team is focused on solving highly complex real-world challenges where reliability, explainability, scalability, and intelligent decision-making are critical. You'll work on systems that move beyond simple chatbot experiences into sophisticated reasoning, planning, retrieval, and workflow automation capabilities.

Success in this role requires a strong engineering mindset, curiosity, and a passion for building the underlying machinery that powers intelligent systems-not just the interfaces users see.

Why Apply?

Work on some of the most exciting areas in modern AI, including Agentic AI, RAG, memory systems, orchestration, and reasoning
Help build production-grade AI systems operating at enterprise scale
Collaborate with highly technical engineers, researchers, and architects
Access modern AI tooling, infrastructure, and platforms
Join a rapidly growing AI organization with significant executive sponsorship and long-term investment
Competitive compensation and strong career growth opportunities