Production AI Agent Developer (Multi-Agent Systems)

Accenture PLC; Calgary; On-site; CAD 100,000 - 217,000; Full time

Job summary

Accenture is seeking an AI Developer (Agentic/Applied) to design, build, and deploy production-grade agentic AI systems across the full enterprise technology stack, collaborating directly with client development teams to deliver scalable patterns and accelerators.

You will lead design sessions, own RAG pipelines, and integrate multiple LLM providers, with emphasis on eval harnesses, observability, and cost management. This role focuses on production deployments and cross-client reuse.

Qualifications

• 7+ years of software development experience in production environments.
• Minimum of 1 year of experience designing and deploying agentic AI solutions in production environments.
• Experience with agentic orchestration frameworks, including LangGraph, CrewAI, AutoGen, or equivalent.
• Experience integrating and calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production systems, including provider abstraction, token management, and cost/latency optimization.
• Experience building and operating RAG pipelines, including embeddings, chunking strategy, vector search, and context design.
• Experience implementing LLM Ops practices, including eval harness design, prompt versioning, and observability tooling.
• Experience with cloud-native systems, including Kubernetes, Docker, microservices, serverless architectures, CI/CD, and infrastructure as code (Terraform or Helm).
• Proficiency in Python; experience with Java or equivalent backend language acceptable
• Experience debugging and monitoring production systems.
• Experience deploying multiple production agentic AI systems.
• Experience defining or standardizing RAG, LLM integration, or LLM Ops practices across projects.
• Experience working directly with client development teams in collaborative development environments.
• Experience building reusable frameworks, accelerators, or delivery playbooks.
• Experience defining and tracking AI system performance metrics such as accuracy, latency, safety, and cost.
• Bachelor’s degree or college diploma in a related field.
• English is required for this position as this role will be aligned to multi-national teams where English is the common language across our North America Market.

Responsibilities

• Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability
• Build and own RAG pipelines: embeddings, chunking strategy, vector search, context window design and tuning against real quality targets
• Integrate and abstract across multiple LLM providers — OpenAI, Anthropic, Vertex AI, and open-source models — with fallback routing, token, cost, and latency management
• Implement LLM Ops in production: eval harnesses with real quality metrics, prompt versioning, observability tooling (LangSmith, Braintrust, or equivalent), cost and safety monitoring
• Embed directly with client development teams to design, prototype, and deploy agentic solutions — workshops, proofs of concept, code-with sessions, and architecture walkthroughs
• Build reusable patterns, accelerators, and playbooks that scale beyond the individual client engagement and enable the next one to start faster
• Define and use metrics to measure agent accuracy, latency, safety, and cost-effectiveness; present findings and recommendations to client stakeholders in business terms

Skills

Software development

Agentic AI

Python

LLM integration

Cloud-native

Kubernetes

Docker

English proficiency

Education

Bachelor's degree

Tools

LangGraph

CrewAI

AutoGen

OpenAI API

Vertex AI

Job description

Accenture is seeking an AI Developer (Agentic/Applied) to design, build, and deploy production-grade agentic AI systems across the full enterprise technology stack, collaborating directly with client development teams to deliver scalable patterns and accelerators.

You will lead design sessions, own RAG pipelines, and integrate multiple LLM providers, with emphasis on eval harnesses, observability, and cost management. This role focuses on production deployments and cross-client reuse.