pIn this role you design, build, and deploy production-grade agentic AI systems at scale for enterprise clients.
You'll work closely with client engineering teams, lead technical design sessions, and create reusable patterns to accelerate future engagements.
The role sits at the intersection of AI engineering and client delivery, with a focus on practical, production-ready solutions.
You will influence architecture choices and drive measurable impact across deployments.
/pulliDesign and build end-to-end production-grade agentic systems (multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, lifecycle observability) /liliOwn RAG pipelines (embeddings, chunking, vector search, context engineering) /liliIntegrate across OpenAI, Anthropic, Vertex AI and open-source models with fallback routing and cost/latency management /liliImplement LLMOps in production (eval harnesses, prompt versioning, observability tooling, cost and safety monitoring) /liliCollaborate with client teams through workshops, proofs of concept, and architecture walkthroughs /liliCreate reusable patterns, accelerators,



and playbooks to scale engagements /liliDefine and report metrics on agent accuracy, latency, safety, and cost-effectiveness to stakeholders /liliMinimum 1 year designing and deploying agentic AI in production /liliExperience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen) at production depth /liliDirect experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code /liliLLMOps fundamentals (eval harness design, prompt versioning, production observability) /liliCloud-native engineering maturity (Kubernetes, Docker, microservices, CI/CD, IaC with Terraform or Helm) /liliStrong Python; Java or equivalent backend language; production debugging and observability /liliProduction-shipped experience preferred over generalist exposure /liliclient collaboration and workshop facilitation /liliability to translate technical findings into business terms /liliproblem solving under production pressure /liliagentic orchestration frameworks (LangGraph, CrewAI, AutoGen) /liliRAG pipelines and vector databases /li /ul #J-*****-Ljbffr

📌 Ai Native Software Engineering Specialist (Latina)
🏢 Accenture
📍 Latina