Description

Key Responsibilities

AI Deployment Recovery & Technical Leadership

Lead turnaround efforts for high-priority customer engagements experiencing AI platform, agent, or deployment issues.

Quickly diagnose root causes and implement remediation plans within fast-paced production environments.

Take ownership of technical delivery and establish engineering best practices across client teams.

Engage directly with senior stakeholders, architects, and executives to communicate risks, solutions, and technical strategies.

AI Agent Engineering & Optimization

Debug and optimize production AI agents built on Google Gemini, GECX, G3, and related AI frameworks.

Design deterministic fallback mechanisms to improve reliability and reduce LLM failure scenarios.

Refactor agent workflows, prompts, and orchestration layers to improve consistency and scalability.

Implement schema validation, structured output handling, guardrails, and workflow controls.

Analyze logs, tracing data, and telemetry to identify and resolve performance bottlenecks.

Software Engineering & System Integration

Refactor and enhance cloud-native microservices using Python, TypeScript/JavaScript, or Go.

Integrate AI agents with enterprise APIs, CRMs, databases, and legacy systems.

Optimize RAG pipelines, vector search architectures, and agent orchestration frameworks.

Improve observability, evaluation metrics, latency, scalability, reliability, and cost efficiency.

Required Qualifications

Software Engineering

6+ years of hands-on software engineering experience.

Strong expertise in Python, TypeScript/JavaScript, or Go.

Experience building and supporting cloud-native applications on Google Cloud Platform (GCP).

Background in distributed systems, APIs, and microservices architecture.

AI & Generative AI Expertise

Proven experience developing and supporting production-grade LLM applications.

Strong knowledge of RAG architectures, vector databases, and AI orchestration frameworks.

Experience with LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or similar frameworks.

Ability to troubleshoot complex AI agent failures and optimize model interactions.

LLM Reliability & Governance

Experience implementing:

Structured JSON outputs

Function/tool calling validation

Prompt engineering and workflow controls

Schema enforcement

Guardrails and safety mechanisms

Deterministic fallback architectures

Enterprise Systems Integration

Experience integrating AI solutions with enterprise applications and legacy platforms.

Background working in regulated industries such as Banking, Healthcare, Insurance, or Financial Services.

Familiarity with compliance frameworks including PCI, HIPAA, and security best practices.

Preferred Qualifications

Prior experience as a Forward Deployed Engineer, Solutions Architect, or AI Consultant at a leading AI, cloud, or consulting organization.

Experience implementing AI governance, fraud detection, compliance, and auditability solutions.

Strong background in AI observability, evaluation frameworks, telemetry, hallucination monitoring, and performance optimization.

Experience supporting enterprise AI transformations and executive-level client engagements.

Desired Traits

Strong problem-solving and troubleshooting mindset.

Comfortable working within ambiguous and complex technical environments.

Exceptional stakeholder management and communication skills.

Proven ability to perform under pressure and drive mission-critical projects to successful outcomes.

Ownership mentality with a strong focus on execution and results.

Quick learner capable of rapidly mastering new technologies and frameworks.

Training & Onboarding

Selected candidates will participate in an intensive hands-on enablement program led by Google AI subject matter experts, covering:

Google GECX & G3 Frameworks

Gemini-Based Agent Development

Deterministic AI Architecture

Advanced Debugging Techniques

Production AI Reliability & Recovery Strategies

Enterprise Account Turnaround Methodologies

Key Skills

Education

Any Gradute