Description

You will build and maintain production-grade machine learning systems, focusing on agentic workflows and LLMOps practices.

This role is on-site.

Responsibilities

• Design and implement multi-agent architectures including planner, researcher, retriever, executor, and reviewer components.
• Build and operationalize Retrieval Augmented Generation (RAG) pipelines, covering ingestion, chunking, embeddings, vector indexing, and retrieval.
• Integrate evaluation and guardrails into systems, monitoring precision, recall, groundedness, and hallucination rates.
• Productionize services on AWS using Lambda, API Gateway, S3, DynamoDB, and Step Functions.
• Drive MLOps and LLMOps practices, managing CI/CD, GitOps, Docker, Kubernetes, and Infrastructure as Code (IaC).

Required Skills

• 5+ years of professional experience in ML/DevOps engineering.
• Proven experience building and deploying agentic systems and production RAG pipelines.
• Strong background working with AWS cloud services for AI/ML workloads.
• Solid experience with CI/CD, Docker, Kubernetes, and IaC principles.
• Experience implementing observability, including tracing, latency monitoring, and A/B testing.
• Familiarity with data governance and model accountability frameworks.
• Proficiency with core tools: CI/CD, GitOps, Docker, Kubernetes, IaC, Lambda, API Gateway, S3, DynamoDB, DevOps.

Preferred Skills

• Experience with AWS Bedrock, OpenSearch, or other vector databases.
• Knowledge of agent frameworks such as LangGraph, crewAI, or AutoGen.

Key Skills

Education

Bachelor's degree