Senior AI Agentic Engineer

Overview

The Senior AI Agentic Engineer designs, builds, and operationalizes intelligent agent systems that automate complex enterprise business processes end-to-end. This role operates at the intersection of large language models (LLMs), systems engineering, and applied machine learning—architecting multi-agent pipelines, tool-augmented reasoning systems, and retrieval-augmented generation (RAG) workflows across enterprise and open-source platforms.

This position requires a hands-on engineering leader with a proven track record of delivering production-grade agentic AI systems at enterprise scale (not just prototypes). The ideal candidate applies rigorous software engineering principles—modular design, testability, resilience engineering, and security-by-design—to create scalable, reliable, and maintainable AI systems.

Success in this role involves architecting for real-world constraints, including failure handling (retries, fallbacks, graceful degradation), latency, and cost efficiency from the outset. Beyond technical delivery, this role mentors engineers, shapes AI automation strategy, and translates complex business challenges into structured, agentic solutions.

Key Responsibilities

Agentic AI System Design & Development

• Design, build, and deploy end-to-end agentic AI systems using LLMs, tools, memory, and planning frameworks to automate complex, multi-step business processes
• Architect both single-agent and multi-agent systems, defining agent roles, memory strategies, tool integrations, and orchestration patterns
• Develop tool-enabled agents with API integrations, structured outputs, database connectors, workflow triggers, and automation hooks
• Integrate AI agents with enterprise systems including ERP platforms, business applications, and orchestration tools

Retrieval-Augmented Generation (RAG)

• Design and optimize RAG pipelines including ingestion, chunking strategies, embeddings, vector databases, and retrieval systems
• Implement advanced retrieval techniques such as hybrid search, metadata filtering, re-ranking, and query optimization
• Continuously improve RAG performance across accuracy, grounding, latency, and cost

Model Adaptation & Prompt Engineering

• Evaluate and deploy frontier and open-source LLMs (e.g., GPT, Claude, Llama, Mistral, Gemini) based on use case requirements
• Optimize prompts, system instructions, and structured outputs for reliability, determinism, and safety
• Apply feedback-driven optimization, including human-in-the-loop and automated evaluation loops

Evaluation, Monitoring & Governance

• Define evaluation frameworks for agentic systems including task success, factual accuracy, latency, and failure modes
• Build observability pipelines to monitor agent behavior, tool usage, and runtime performance
• Partner with governance and compliance teams to ensure responsible AI practices, auditability, and data protection

Production Deployment & LLMOps

• Deploy AI systems using cloud-native architectures (Azure, AWS, or GCP) with containerized infrastructure (Docker/Kubernetes)
• Implement CI/CD pipelines, prompt/version management, rollback strategies, and runtime safeguards
• Optimize systems for scalability, cost efficiency, and production performance

Collaboration, Mentorship & Strategy

• Collaborate with engineering, product, data, and business teams to translate complex problems into agentic solutions
• Mentor engineers on best practices for agentic system design and responsible AI
• Contribute to AI strategy, technical roadmaps, and governance standards
• Stay current on emerging tools, frameworks, and research in the agentic AI space

Required Qualifications

Technical – Agentic AI & LLMs

• Proven experience delivering production-grade multi-agent AI systems that automate real business workflows
• Hands-on expertise with agent orchestration frameworks (e.g., LangChain, LangGraph, AutoGen, Semantic Kernel, CrewAI, or equivalent)
• Deep understanding of LLM capabilities, limitations, and appropriate use cases
• Experience with structured outputs, function calling, and multi-step agent workflows

Technical – Data & RAG

• Strong experience with RAG architectures, vector databases (e.g., Pinecone, Weaviate, pgvector), and embedding models
• Experience working with enterprise data platforms, databases (SQL), and cloud storage systems

Technical – Engineering & Deployment

• Strong proficiency in Python and building production-grade APIs/microservices
• Experience deploying AI workloads on cloud platforms (Azure, AWS, or GCP) using containerization
• Experience with LLMOps practices including experiment tracking, prompt versioning, evaluation frameworks, and CI/CD
• Familiarity with enterprise security, data governance, and compliance requirements

Evaluation & Responsible AI

• Experience with evaluation techniques, failure mode analysis, and testing of AI systems
• Understanding of responsible AI principles including fairness, safety, explainability, and human oversight

Leadership & Communication

• Strong communication skills with ability to explain complex AI concepts to technical and non-technical audiences
• Experience leading cross-functional initiatives from concept through production
• Ability to mentor teams and drive engineering standards
• Strong problem-solving skills with ability to structure ambiguous business challenges into clear solutions

Education & Experience

• 7+ years of experience in AI, data science, software engineering, or related fields
• 3+ years working specifically with LLMs, GenAI, or agentic AI systems
• Bachelor’s degree required in Computer Science, Engineering, Data Science, or related field
• Master’s degree preferred