Senior Forward-Deployed AI Engineer | GCP & LLM Systems

Aviato Consulting Pty Ltd; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Best Place to Work awards

Vertex AI ecosystem access

Ex-Googler collaboration

Strong engineering culture

Job summary

Aviato Consulting Pty Ltd seeks a Forward Deployed Engineer to code, integrate, and deploy custom, production-ready enterprise solutions in complex environments. You will bridge Google Cloud AI capabilities and live customer infrastructure.

Join an elite engineering culture with ex-Googlers, gain full access to Vertex AI ecosystem, and contribute to RAG pipelines, agent architectures, and scalable AI/ML deployments. Focus on security, observability, and customer leadership.

Qualifications

• Bachelor's degree in CS or related field, or equivalent practical experience.
• 5+ years of professional software development in Python or Go with microservices and API design.
• 3+ years AI experience building scalable apps on GCP and production-grade ML workflows.
• Experience with RAG pipelines, vector search, and cloud-native architectures.

Responsibilities

• ADK Framework Integration: design modular agent architectures using Google's ADK.
• Telemetry & Observability: set up tracing, logging, and monitoring for agent workflows.
• Human-in-the-Loop Safeguards: implement oversight checkpoints and fallback mechanisms.
• Data Architecture & Privacy: engineer RAG pipelines with privacy controls and residency requirements.
• Customer Technical Leadership: guide customers through discovery, reviews, and deployments.

Skills

Python

Go

Asynchronous programming

Microservices

API design

AI/ML deployment

RAG pipelines

Vector search

Vertex AI

AlloyDB

Memorystore Redis

Cloud Run

Cloud Functions

Education

Bachelor's degree in Computer Science or related field

Tools

Vertex AI

AlloyDB

Memorystore Redis

Cloud Run

Cloud Functions

Job description

Those interested should apply directly through our careers page :

https://aviato.jobs.growhire.com/jobs/cmq4ol08f04x0bcka8a1nenn0

We are proud winners of the Best Place to Work awards in 2025 and 2026. Aviato Consulting, specializes in Google Cloud solutions. We combine deep technical expertise with an open, fun engineering culture.

We are seeking a Forward Deployed Engineer to code, integrate, and deploy custom, production-ready enterprise solutions in complex environments. In this role, you will bridge the gap between cutting-edge Google Cloud AI capabilities and live customer infrastructure.

What's in it for you?

• Build the "Next" Tech: Working heavily on AI, you will be using the newest models, to build agents to solve our customers problems.
• Elite Engineering Culture: Work alongside ex-Googlers and cloud experts. We prioritize clean code, high velocity shipping, and technical excellence over politics.
• Pure GCP Playground: You get full access to the Vertex AI ecosystem (Gemini 3 Pro/Flash, Claude, Vector Search, Agent Engine) to build solutions.
• Verified Happiness: Join a team objectively recognized as a "Best Place to Work" for two years running. We take culture as seriously as we take our architecture.

Role Description

• ADK Framework Integration: Design and implement modular agent architectures using Google's Agent Development Kit (ADK) to build standardized, maintainable agentic workflows.
• Telemetry & Observability: Set up distributed tracing, structured logging, and real-time monitoring for full visibility into agent logic, tool calls, latency, and operational costs.
• Human-in-the-Loop Safeguards: Design human oversight checkpoints, confidence scoring thresholds, and automated fallback mechanisms for critical enterprise actions.
• Data Architecture & Privacy: Engineer retrieval-augmented generation (RAG) pipelines and memory systems while enforcing data classification, privacy controls, and residency requirements.
• Customer Technical Leadership: Guide customer teams through technical discovery, architecture reviews, and production deployments while instilling Google-grade engineering standards.

What You'll Bring to the Table:

• Bachelors degree in Computer Science, Software Engineering, or equivalent practical experience.
• 5+ years of professional software development experience in Python or Go, with production expertise in asynchronous programming, microservices, and API design.
• 3+ years of hands-on AI experience building and deploying scalable applications on Google Cloud Platform (GCP).
• Proven track record architecting and launching production-grade AI/ML applications, LLM workflows, or Agentic systems from concept through post-go-live support.
• Hands-on experience developing Retrieval-Augmented Generation (RAG) pipelines and vector search architectures (e.g. Vertex AI Vector Search, AlloyDB, Memorystore Redis).
• Strong working knowledge of core GCP infrastructure: Cloud Run, Cloud Functions, Pub/Sub, Cloud Storage, BigQuery, IAM, and VPC Service Controls (VPC-SC).
• Experience leading technical discovery, code reviews, and architecture deep-dives with customer technical teams.

Bonus Points:

• Experience implementing multi-agent systems using frameworks (e.g., LangGraph, CrewAI, ADK) and patterns (e.g., ReAct, self-reflection, hierarchical delegation).
• Knowledge of LLM-native metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing.
• Google Cloud Certified (e.g., Professional Cloud Architect or Professional Machine Learning Engineer).
• Experience with Apigee for API management, security, and integration within GCP environments.

Our Core Values:

We operate with radical transparency, believe in rigorous teamwork , prioritize continuous excellence and growth, and deliver exceptional value as dedicated client partners.