Architect a high-throughput Retrieval-Augmented Generation (RAG) pipeline that ingests streaming telemetry, PCAP files, and syslog data into Vector Databases for real-time agent context. • Network ...
Architect a high-throughput Retrieval-Augmented Generation (RAG) pipeline that ingests streaming telemetry, PCAP files, and syslog data into Vector Databases for real-time agent context. • Network ...
Experience with Retrieval-Augmented Generation (RAG), Vector Databases, and Prompt Engineering. * Familiarity with MLOps tools and model deployment frameworks. * Experience with Docker, Kubernetes ...
Experience with Retrieval-Augmented Generation (RAG), Vector Databases, and Prompt Engineering. * Familiarity with MLOps tools and model deployment frameworks. * Experience with Docker, Kubernetes ...
Gen AI Tech Lead
Tampa, FL · On-site
... Retrieval-Augmented Generation (RAG) systems and techniques. • Experience designing and implementing agentic AI architectures, autonomous workflows, or multi-agent systems. • Familiarity with ...
Gen AI Tech Lead
Tampa, FL · On-site
... Retrieval-Augmented Generation (RAG) systems and techniques. • Experience designing and implementing agentic AI architectures, autonomous workflows, or multi-agent systems. • Familiarity with ...
Delivery Senior Consultant, Software Engineering Solutions, Identity & Gen AI Engineer
$107K - $141K/yr
... retrieval-augmented generation (RAG), or AI agents, including use of model APIs, orchestration frameworks, and AI development tools such as Claude Code, OpenAI Codex, GitHub Copilot, or Cursor
Delivery Senior Consultant, Software Engineering Solutions, Identity & Gen AI Engineer
$107K - $141K/yr
... retrieval-augmented generation (RAG), or AI agents, including use of model APIs, orchestration frameworks, and AI development tools such as Claude Code, OpenAI Codex, GitHub Copilot, or Cursor
Define end-to-end architectures for complex Gen AI solutions, including Retrieval-Augmented Generation (RAG) pipelines, multimodal models, and autonomous multi-agent systems Reusable Patterns:
Define end-to-end architectures for complex Gen AI solutions, including Retrieval-Augmented Generation (RAG) pipelines, multimodal models, and autonomous multi-agent systems Reusable Patterns:
... retrieval-augmented generation (RAG), and context management. Solution Development • Build end-to-end AI applications using Python, integrating with APIs, databases, and cloud-native services. • ...
... retrieval-augmented generation (RAG), and context management. Solution Development • Build end-to-end AI applications using Python, integrating with APIs, databases, and cloud-native services. • ...
... using Retrieval-Augmented Generation (RAG). • Hands-on knowledge of Chain-of-Thoughts, Tree-of-Thoughts, Graph-of-Thoughts prompting strategies. Skills: Digital : Python~Digital : Artificial ...
... using Retrieval-Augmented Generation (RAG). • Hands-on knowledge of Chain-of-Thoughts, Tree-of-Thoughts, Graph-of-Thoughts prompting strategies. Skills: Digital : Python~Digital : Artificial ...
Gen AI Tech Lead
Tampa, FL · On-site
$132K - $162K/yr
... Retrieval-Augmented Generation (RAG) systems and techniques. • Experience designing and implementing agentic AI architectures, autonomous workflows, or multi-agent systems. • Familiarity with ...
Gen AI Tech Lead
Tampa, FL · On-site
$132K - $162K/yr
... Retrieval-Augmented Generation (RAG) systems and techniques. • Experience designing and implementing agentic AI architectures, autonomous workflows, or multi-agent systems. • Familiarity with ...
... RAG (Retrieval-Augmented Generation) pipelines seamlessly within existing .NET ecosystems. • Hands-on configuration and utilization of PostgreSQL with Docker and pgvector for efficient, secure ...
... RAG (Retrieval-Augmented Generation) pipelines seamlessly within existing .NET ecosystems. • Hands-on configuration and utilization of PostgreSQL with Docker and pgvector for efficient, secure ...
Build advanced Retrieval-Augmented Generation (RAG) architectures, including hybrid retrieval, query planning, and retrieval optimization. * Develop, tune, and deploy applications leveraging major ...
Build advanced Retrieval-Augmented Generation (RAG) architectures, including hybrid retrieval, query planning, and retrieval optimization. * Develop, tune, and deploy applications leveraging major ...
AI Engineer
Jacksonville, FL · On-site
Basic RAG implementations (embeddings + vector search for retrieval-augmented generation) * Strong discipline around AI evaluation and reliability , including: * Testing prompts and multi-step chains
AI Engineer
Jacksonville, FL · On-site
Basic RAG implementations (embeddings + vector search for retrieval-augmented generation) * Strong discipline around AI evaluation and reliability , including: * Testing prompts and multi-step chains
Analyst, AI Engineer
Hollywood, FL · On-site
Build and support retrieval-augmented generation (RAG), embeddings, vector search, document ingestion pipelines, prompt workflows, and AI assistant capabilities for internal users and distributor ...
Quick apply
Analyst, AI Engineer
Hollywood, FL · On-site
Build and support retrieval-augmented generation (RAG), embeddings, vector search, document ingestion pipelines, prompt workflows, and AI assistant capabilities for internal users and distributor ...
Implement RAG (Retrieval-Augmented Generation) applications to enhance AI systems with dynamic information retrieval. * Build and integrate AI agentic frameworks for autonomous decision-making and ...
Implement RAG (Retrieval-Augmented Generation) applications to enhance AI systems with dynamic information retrieval. * Build and integrate AI agentic frameworks for autonomous decision-making and ...
AI/ML Engineer
Aventura, FL · On-site
Implement RAG (Retrieval-Augmented Generation) applications to enhance AI systems with dynamic information retrieval. * Build and integrate AI agentic frameworks for autonomous decision-making and ...
AI/ML Engineer
Aventura, FL · On-site
Implement RAG (Retrieval-Augmented Generation) applications to enhance AI systems with dynamic information retrieval. * Build and integrate AI agentic frameworks for autonomous decision-making and ...
Develop and optimize Retrieval-Augmented Generation (RAG) systems, including embeddings, vector search, retrieval pipelines, chunking strategies, and relevance tuning. * Build multimodal AI workflows ...
Quick apply
Develop and optimize Retrieval-Augmented Generation (RAG) systems, including embeddings, vector search, retrieval pipelines, chunking strategies, and relevance tuning. * Build multimodal AI workflows ...
AI Architect
Tampa, FL · On-site
Establish standards for building LLM applications, retrieval-augmented generation (RAG) systems, intelligent agents and ML models at scale * Create reference architectures for AI-powered solutions ...
AI Architect
Tampa, FL · On-site
Establish standards for building LLM applications, retrieval-augmented generation (RAG) systems, intelligent agents and ML models at scale * Create reference architectures for AI-powered solutions ...
AI Architect
$59.50 - $78.50/hr
Establish standards for building LLM applications, retrieval-augmented generation (RAG) systems, intelligent agents and ML models at scale* Create reference architectures for AI-powered solutions ...
AI Architect
$59.50 - $78.50/hr
Establish standards for building LLM applications, retrieval-augmented generation (RAG) systems, intelligent agents and ML models at scale* Create reference architectures for AI-powered solutions ...
AI Agent Engineer
Dania, FL · On-site
... retrieval-augmented generation (RAG) patterns in production contexts. • Experience with voice-specific technical concepts including ASR/TTS configuration, telephony integration, DTMF handling, and ...
AI Agent Engineer
Dania, FL · On-site
... retrieval-augmented generation (RAG) patterns in production contexts. • Experience with voice-specific technical concepts including ASR/TTS configuration, telephony integration, DTMF handling, and ...
... Retrieval Augmented Generation (RAG) and agent based architectures. • Familiarity with AI safety, governance, and responsible AI principles. • Experience developing AI powered platform components ...
... Retrieval Augmented Generation (RAG) and agent based architectures. • Familiarity with AI safety, governance, and responsible AI principles. • Experience developing AI powered platform components ...
MLOps Engineer
Orlando, FL · On-site
... retrieval-augmented generation (RAG), or embedding pipelines • Exposure to managing and monitoring ML workloads that support generative AI or advanced analytics use cases • Proficiency with ...
MLOps Engineer
Orlando, FL · On-site
... retrieval-augmented generation (RAG), or embedding pipelines • Exposure to managing and monitoring ML workloads that support generative AI or advanced analytics use cases • Proficiency with ...
Retrieval Augmented Generation Rag information
Contractor
Posted 27 days ago
Job description
Location: ONSITE-
Duration: 6 months
Role: Java Full Stack
Descriptions:
Must Have Technical/Functional Skills
• Reduction in MTTR (Mean Time to Repair): Speed of autonomous fault correlation and resolution via
agentic workflows.
• Provisioning Accuracy: Zero-touch fulfillment success rate without manual intervention or
configuration drift.
• Guardrail Efficacy: Percentage of "unsafe" or "hallucinated" network commands intercepted by the
safety layer before execution.
• Agentic Efficiency: Token-to-action cost optimization for high-frequency network monitoring tasks
• As the Lead AI Architect for Telecom, you will design the brain of our next-generation autonomous
network.
• You will build an AI platform where Agentic AI acts as the orchestration layer for network service
fulfillment, closed-loop assurance, and predictive maintenance.
• Your goal is to move the organization from "Human-in-the-loop" to "Human-on-the-loop,
• Ensuring AI agents can safely execute commands across IP, Optical (DWDM/OTN), and Wireless
infrastructures
Roles & Responsibilities
Agentic Network Orchestration
• Autonomous Fulfillment: Architect multi-agent systems that can take a high-level service request (e.g.,
"Provision a 100G Wavelength service") and decompose it into specific CLI/API commands across multi-
vendor environments.
• Intent-Based Networking (IBN): Develop reasoning engines that translate natural language business
intents into technical configurations using frameworks like LangGraph or CrewAI.
• Troubleshooting Agents: Design "Diagnostic Agents" that can autonomously query telemetry data,
correlate alarms, and suggest (or execute) remediation steps for network outages.
2. Data Architecture for Telco AI
• Real-time Telemetry RAG: Architect a high-throughput Retrieval-Augmented Generation (RAG) pipeline
that ingests streaming telemetry, PCAP files, and syslog data into Vector Databases for real-time agent
context.
• Network Digital Twin Integration: Connect AI agents to Digital Twins and Graph Databases (Neo4j) to
ensure they "understand" physical and logical topology before making routing changes.
• Unified Data Fabric: Build the data architecture necessary to bridge silos between Radio Access
Network (RAN), Core, and Edge data.
3. Telco-Grade Guardrails & Safety
• Deterministic Execution: Implement strict guardrails (e.g., NeMo, Guardrails AI) to ensure agents never
execute a command that violates "Golden Configuration" standards.
• SLA-Aware Governance: Architect systems that monitor agent actions against Service Level
Agreements (SLAs), ensuring autonomous decisions do not prioritize one customer's traffic at the
expense of a higher-priority emergency service.
• Policy Enforcement: Design a "Policy Proxy" layer where every agentic action is validated against a library of telecom regulatory and security compliance rules.
Keyword:
Skills: Digital : ReactJS~Digital : Spring Boot
Experience Required: 8-10, Project Code :
About Real Soft
Sourced by ZipRecruiter
Industry
It services
Company size
501 - 1,000 Employees
Headquarters location
Monmouth Junction, NJ, US
Year founded
1991