Senior AI Engineer (Agentic AI)

PM Consulting; Philippines; On-site; PHP 1,200,000 - 1,800,000; Full time

Job summary

PM Consulting is seeking a Senior AI Engineer to architect agent workflows and integrate LLMs within enterprise APIs. You will build robust backends, manage tool calls, and ensure production-grade reliability in a secure cloud environment.

The role focuses on multi-step agent orchestration, RAG-style data retrieval, and governance-driven deployment with strong emphasis on Azure-based platforms and scalable architectures.

Qualifications

• 4+ years building backend or service architectures.
• Hands-on experience with large language models in production.
• Strong debugging across distributed APIs and async data.

Responsibilities

• Design and implement multi-step agent workflows with tool-chaining.
• Integrate LLMs (Claude/OpenAI) with enterprise APIs and microservices.
• Ensure reliability with retries, fault tolerance, and observability.
• Develop human-in-the-loop validation and governance controls.

Skills

C# and/or Python

Azure

LLM Integration

Agent Orchestration

Vector databases

RESTful APIs

Education

Bachelor's degree in CS or related field

Tools

Azure AI Foundry

LangGraph

LangChain

Pinecone

Job description

About the job Senior AI Engineer (Agentic AI)

Our client, a leading enterprise enterprise, is seeking a Senior AI Engineer specializing in Agentic Workflows and LLM Integration. This specialized engineering role sits at the cutting edge of AI innovation, commanding an organization-wide mandate to design, deploy, and own multi-step autonomous agent systems. The successful candidate will build robust backend infrastructures, orchestrate tool-calling logic, and manage advanced retrieval architectures to deliver resilient, production-grade AI applications within an enterprise framework.

Key Accountabilities

AI Architecture & Agent Workflow Engineering

• Agent Execution Patterns: Design, build, and test highly complex, multi-step agent workflows utilizing established advanced architectural design patterns such as ReAct, planner-executor, and complex tool-chaining.
• LLM Core Integration: Integrate flagship Large Language Models (including Anthropic Claude and OpenAI) with legacy enterprise APIs and internal microservices, engineering robust fault tolerance for retries, edge cases, and degraded ecosystem states.
• Orchestration & Failure Resilience: Implement programmatic tool calling, function orchestration pipelines, and automated compensating actions to guarantee agent workflows remain stable under catastrophic or unexpected third-party failure conditions.
• Human-in-the-Loop Controls: Architect and deploy conditional human-in-the-loop validation frameworks, including automated executive approvals, smart escalations, and exception-handling logic mandated by business governance or risk considerations.

Data Engineering, Prompts & Retrieval (RAG)

• Context & Memory Architecture: Build and manage advanced agent memory retention layers and data retrieval mechanisms utilizing vector databases and Retrieval-Augmented Generation (RAG), tuning indexing schemas to ensure relevant context.
• Prompt Management: Develop, maintain, optimize, and version-control complex prompt logic, semantic routing rules, and supporting technical documentation in accordance with strict enterprise engineering standards.

Production Deployment, Security & Observability

• Cloud Operations: Deploy mission-critical AI services into production cloud environments, actively monitoring logs, distributed traces, and telemetry metrics to rapidly isolate and patch behavioral anomalies.
• Enterprise Governance: Ensure all deployed solutions strictly mirror enterprise-grade security controls, identity management requirements, and rigorous data governance protocols.
• Reliability Engineering: Partner with QA and Core Operations teams to continually upgrade automated test coverage, build out operational runbooks, establish incident response protocols, and drive system performance optimizations.

Requirements

Education & Experience

• Technical Tenure: Minimum of 4 years of hands-on experience developing backend or service-based software architectures using C# and/or Python.
• AI Specialization: At least 1 year of production-level experience working directly with large language models, structured prompt engineering frameworks, or agentic AI-enabled systems.
• Analytical Reasoning: Elite debugging skills with a proven capacity to reason across distributed APIs, asynchronous data flows, and non-deterministic AI system behaviors.

Technical Skills (Required)

• Programming Ecosystems: Production-grade fluency in C# and/or Python, including async workflow patterns, service building, and automated test frameworks.
• Cloud Platform: Microsoft Azure (encompassing compute, scalable storage, IAM identity models, and automated deployment pipelines).
• LLM Integration & Tooling: Direct integration with Claude and/or OpenAI APIs (handling tool calling, prompt tokenization, rate limit mitigation, and state error handling).
• Agent Orchestration Frameworks: Experience using Azure AI Foundry or Microsoft Agent Framework. Hands-on knowledge of LangGraph or LangChain is highly valued.
• Vector Architectures: Experience with Pinecone or equivalent vector databases (handling structural indexing, query retrieval, and semantic relevance tuning).APIs & Identity: RESTful API design, enterprise-grade service authentication, and secure service-to-service integrations.
• Observability Suites: Distributed application logging, performance metrics tracking, and transaction tracing in production scales.

Preferred Qualifications (Desirable)

• Containerization deployments utilizing Docker and Azure Container Services (AKS/ACA).
• Experience architecting relational databases (SQL Server) and NoSQL document stores (Azure Cosmos DB).
• Prior experience operating within highly regulated, compliance-driven, or audit-heavy corporate environments.
• Foundational understanding of emerging AI Governance and AI Security (OWASP Top 10 for LLMs) paradigms.