Senior AI/ML Engineer AI Platform & RAG Systems

Job Summary

Seeking a Senior AI/ML Engineer with strong experience in building scalable AI platforms, retrieval-augmented generation (RAG) systems, and production-grade ML/data pipelines for enterprise environments. The ideal candidate will have deep expertise in AI/ML engineering, cloud-native architecture, data engineering, and deploying secure, scalable solutions into production.

Key Responsibilities

• Design and build multi-tenant AI platforms, including agentic workflows, RAG services, and LLM orchestration.
• Develop LLM-powered applications for intelligent automation, enterprise search, and knowledge retrieval.
• Implement and optimize vector search and retrieval pipelines using OpenSearch kNN, metadata indexing, and hybrid search.
• Build secure, event-driven ingestion pipelines integrating data lakes, streaming systems, and document processing workflows.
• Design advanced chunking and document parsing strategies to improve retrieval relevance across multiple file types.
• Develop LLM evaluation pipelines, golden datasets, custom evaluators, and explainable scoring mechanisms.
• Implement feedback and human-in-the-loop systems to improve AI performance in production.
• Establish observability for AI systems, including tracing, latency monitoring, token usage, and model performance insights.
• Build and optimize batch and real-time data pipelines for ML and analytics workloads.
• Implement MLOps practices for model training, deployment, versioning, and monitoring.
• Ensure security, governance, compliance, and responsible AI controls across enterprise deployments.
• Partner with architecture, product, and security teams to define readiness criteria and production rollout plans.

Required Qualifications

• 10+ years of overall IT experience with strong focus on AI/ML engineering, data engineering, or platform engineering.
• Strong hands-on programming experience in Python and SQL.
• Proven experience building RAG systems, LLM-based applications, and AI orchestration workflows.
• Strong knowledge of vector databases or vector search technologies such as OpenSearch kNN or similar platforms.
• Experience building ETL/ELT and ML-ready data pipelines using Spark, PySpark, or similar big data frameworks.
• Hands-on experience with streaming technologies such as Kafka, Kinesis, or Event Hub.
• Experience with MLOps tools and deployment frameworks such as MLflow, Docker, Kubernetes, and CI/CD pipelines.
• Strong experience with AWS and/or Azure cloud ecosystems.
• Experience implementing observability, monitoring, and evaluation frameworks for AI systems.
• Knowledge of secure enterprise architecture including RBAC, OAuth2, PII handling, and compliance controls.
• Bachelor s or Master s degree in Computer Science, Engineering, or a related field.

Preferred Qualifications

• Experience with enterprise AI platforms such as C3.ai, AWS AI, or Azure AI services.
• Familiarity with agentic AI, multi-agent systems, and tool-based LLM workflows.
• Experience with Delta Lake, Snowflake, OpenSearch, and modern cloud data platforms.
• Exposure to regulated industries such as banking, healthcare, or financial services.
• Experience with Terraform, ArgoCD, autoscaling frameworks, and cloud-native infrastructure.
• Ability to translate business requirements into scalable, production-ready AI solutions.