Technical Architect · AI Agent Engineer · Voice AI Specialist · Full Stack Developer

Hi, I'm

Riccardo Germanà

I design agentic AI systems, enterprise architectures and full-stack applications. I turn complex problems into products that actually work.

Learn More>Get in Touch
Scroll to explore

I build intelligence that acts

Technical Architect and AI Engineer with 9+ years of experience. I combine enterprise architecture, agentic AI and voice technology to create solutions that make a difference. My strength is the 360° vision: from model to deployment, from protocol to pixel.

at a glance
Years on enterprise delivery
9+
Salesforce Certifications
14
  • 01
    Architecture
    Distributed, multi-tenant, scalable systems. Built to last.
  • 02
    Agentic AI
    Autonomous agents with tool calling, RAG, MCP and multi-agent orchestration.
  • 03
    Voice & Real-time
    AI conversations integrated with telephony, contact centers and enterprise workflows.
  • 04
    Enterprise Integration
    Salesforce, MuleSoft, contact centers. Systems that talk to each other.

Journey

2017–2020

Full Stack Developer

Custom web projects with JavaScript, React, Angular, Node.js, Java, .NET. Frontend, backend, REST APIs, and DevOps.

2020–2022

Salesforce Developer

Specialized in Apex, LWC, Flows for enterprise clients. First Salesforce certifications.

2022–2024

Technical Architect — BIP

Scalable CRM architectures, MuleSoft integrations, team coordination. Grew to 14 Salesforce certifications.

2024–Today

AI Engineer & Architect

Agentic systems, voice AI, custom MCP servers. I build AI that acts, not just answers.

Not just chatbots.
AI that acts.

I design end-to-end agentic systems: agents that reason, call tools, orchestrate flows and make autonomous decisions. Specialized in real-time voice AI, MCP servers and agent fleets with quality gates.

01

Agent Engineering

Single and multi-agent systems with tool calling, function calling, persistent memory. Orchestration with team-lead pattern and manual quality gates.

Pydantic AIVercel AI SDKOpenCodeMulti-Agent
02

Real-time Voice AI

Complete voice pipelines: STT, VAD, LLM, TTS, turn-taking and SIP telephony. Contact center and enterprise integrations like Salesforce.

ElevenLabsLiveKitDeepgramWebRTC
03

MCP — Model Context Protocol

I build custom MCP servers to expose tools, resources and knowledge bases to LLMs. MCP clients integrated into production agents.

MCP SDKTool ServersResource Servers
04

RAG & Knowledge

RAG systems with hybrid search (FTS + semantic), pgvector, Qdrant, local embeddings, version-aware retrieval. Knowledge bases that scale.

pgvectorQdrantEmbeddingsHybrid Search
05

LLM Orchestration

Multi-provider routing (Claude, GPT, Gemini, Grok), structured prompt engineering, automated evals, A/B testing on prompts and models.

ClaudeOpenAIGeminiRouting
06

Production AI Ops

Observability (OpenTelemetry, Sentry), hypothesis-driven test loops, guardrails, cost management, multi-tenant enterprise deploys with full audit.

OTelEvalsGuardrailsMulti-tenant

Selected work

Anonymous (NDA-safe) case studies of systems I've architected and shipped. Enterprise voice agents, MuleSoft integrations, AI automation and agent tooling.

01Automotive · national leader

Enterprise voice agent

70+ locations, voice customer service · Technical Architect & Delivery Lead

Automate voice customer service at national scale without losing quality, keeping human handoff on complex cases and integration with the existing CRM.

Trade-off · Direct SIP routing over PSTN; RAG on a knowledge base over fine-tuning; guardrails and human handoff non-negotiable on sensitive cases.

Esito · 24/7 service, human handoff preserved, across 70+ locations with centralized cloud orchestration.

ElevenLabsSalesforceQdrantAWSSIP
  1. ChannelsSIP telephony · multi-site routing
  2. Voice platformElevenLabs Conv AI · ASR/TTS
  3. OrchestrationLLM · RAG · guardrails · turn-taking
  4. Knowledge baseQdrant · semantic retrieval
  5. IntegrationsSalesforce Service Cloud · human handoff
01 · architecture
02Mobility · national leader

API-led integration suite

10 service areas, 13 systems · Integration Architect

Integrate loyalty, ERP, ticketing, billing and 10+ legacy systems into a coherent, maintainable architecture, in production.

Trade-off · API-led layering to decouple legacy; RAML contracts as source of truth; CDC for near-realtime sync across domains.

Esito · Suite in production across 10 service areas, legacy systems decoupled, reusable API contracts.

MuleSoftCloudHubDataWeaveRESTRAML
  1. Experience APIWeb · mobile · partner
  2. Process APILoyalty · pricing · orders
  3. System APISalesforce · ERP · legacy
  4. RuntimeMuleSoft CloudHub · DataWeave
02 · architecture
03Energy · regulated tariffs

AI automation with quality gates

Document BPO automation · AI Engineer & Architect

Automate parsing and normalization of regulated documents (ARERA/Terna) with high accuracy and full compliance.

Trade-off · Deterministic parser first, LLM only as fallback; mandatory human validation; 55 regression tests as guardrail.

Esito · Automation with explicit quality gates, full traceability, aligned with compliance requirements.

PythonFastAPINext.jsLLMHITL
  1. IngestionRegulated docs · multi-format
  2. ParserContent-driven · deterministic
  3. LLM fallbackUnstructured cases
  4. HITL validationHuman-in-the-loop mandatory
  5. OutputStructured · versioned · auditable
03 · architecture
04R&D · internal tooling

Agent framework & MCP server

3 MCP servers, 44+ tools · AI Engineer · Builder

Boost team efficiency with agents that automate analysis, documentation and deployment of enterprise platforms (Salesforce, MuleSoft).

Trade-off · Local version-aware RAG (220K+ chunks); entire APIs exposed as LLM tools; manual quality gates before merge.

Esito · 3 MCP servers in production, automation of the enterprise integration lifecycle, automated platform assessments.

MCPTypeScriptRAGMulti-Agent
  1. MCP serverElevenLabs API · MuleSoft RAG · Knowledge base
  2. Agent frameworkMulti-agent · team-lead pattern
  3. ToolingCLI · IDE integration
  4. Quality gateEvals · manual review
04 · architecture
05Side project · personal

CoBrain

Local-first meeting copilot · Solo developer

A copilot for Teams meetings that transcribes, diarizes and indexes into a local knowledge base, without ever sending data to third-party servers.

Trade-off · Fully local by principle (privacy-first); sherpa-onnx for on-device diarization; RAG on a personal vault instead of cloud LLMs.

Esito · Transcripts, diarization and semantic search over your own meetings, with data never leaving the device.

PythonSwiftWhisperRAGLocal-first
  1. CaptureTeams · ASR streaming
  2. ASR + diarizationWhisper · sherpa-onnx
  3. Knowledge baseLocal RAG · personal vault
  4. ClientSwift · local-first
05 · architecture
06Side project · open source

SF Analyzer

Agentic AI for Salesforce orgs · Creator · Solo developer

Automate the analysis, documentation and assessment of complex Salesforce orgs through a fleet of specialized AI agents.

Trade-off · Team-lead pattern with domain-specialized agents; manual quality gates before merge; v2 pivoting local-first.

Esito · v1 in production: automated analysis of complex orgs, documentation generated and validated by leader agents.

TypeScriptReactVercel AI SDKMulti-AgentSalesforce
View repository →
  1. Agent fleet9 documentor · 3 leader
  2. OrchestrationTeam-lead pattern · quality gate
  3. BackendNode.js · TypeScript · PostgreSQL
  4. ClientReact · Vercel AI SDK
06 · architecture

Full stack

Polyglot full-stack: AI, web, mobile, enterprise. I pick the right tool for the problem, not the problem for the tool.

01

AI & LLM

ClaudeOpenAIGeminiGrokPydantic AIVercel AI SDKMCPLangChain
02

Voice AI

ElevenLabsLiveKitDeepgramWhisperSilero VADWebRTCSIPTwilio
03

Frontend

ReactNext.jsAstroSolidJSTypeScriptTailwindMotionshadcn/ui
04

Backend

Node.jsFastifyFastAPINestJSPythonRustJava SpringGraphQL
05

Salesforce

ApexLWCFlowsSales CloudService CloudMarketing CloudData CloudAgentforce
06

Integration

MuleSoftAnypointDataWeaveRAMLREST APISOAPEvent-DrivenWebhooks
07

Database

PostgreSQLpgvectorQdrantMongoDBRedisSQLitePrismaSQLAlchemy
08

DevOps & Cloud

DockerKubernetesAWSAzureCI/CDTerraformOpenTelemetryLinux

How I build

A process that combines enterprise rigor and startup speed. Every phase has explicit quality gates.

01

Discovery

I understand the real problem, not just requirements. Stress-test assumptions, map constraints, define measurable success.

02

Architecture

I design the solution: pattern selection, data model, API contracts, AI strategy. Decisions documented as ADRs.

03

Slicing

Decompose into independent vertical slices (tracer bullets). Each slice delivers end-to-end value and ships on its own.

04

Build

TDD where it makes sense, AI-augmented always. Type-safe end-to-end, observability by default, hypothesis-driven testing.

05

Verify

Automated evals for AI, E2E tests for the rest. Quality gates before every merge. No claims without fresh evidence.

06

Ship & Learn

Feature-flagged deploys, real-time monitoring, structured post-mortems. Every release improves the system and the process.

Let's work together

Got an AI idea, a system to architect, an agent to build? Let's talk.

direct
follow