Software Engineer

STRATEGIC STAFFING SOLUTIONS HAS AN OPENING!

This is a Contract Opportunity with our company that MUST be worked on a W2 Only. No C2C eligibility for this position. Visa Sponsorship is Available! The details are below.

“Beware of scams. S3 never asks for money during its onboarding process.”

Job Title: Software Engineer
Contract Length: 24+ Months
Location: Chandler, AZ

Job ref# 243997

Overview

• Will design, build, and optimize advanced conversational systems leveraging Google Cloud Platform and next-generation Agentic AI This role involves deep expertise in multi-agent orchestration, prompt engineering, and real-time, low-latency architecture for large-scale GenAI deployments.
• The ideal candidate has a proven record of delivering production-grade LLM-driven solutions, designing robust guardrails, and implementing Responsible AI (RAI) practices for regulated environments such as FinTech or healthcare.

Key Responsibilities

• Design & Development:
• Build and maintain conversational agent platforms on GCP, leveraging Playbooks, connectors, data sources, and prompt engineering strategies.
• Implement multi-agent orchestration using frameworks such as LangGraph, LangChain (with ReACT), and other LLM tooling.
• Extend conversational context and state across sessions using BigTable, Pub/Sub, Kafka, and time-series data systems.
• Scalable Architecture:
• Engineer massive-scale, low-latency, real-time architectures focused on eventing and dynamic conversational memory.
• Integrate AI-driven microservices with GCP-native technologies including AlloyDB, BigTable, and Pub/Sub for event-driven systems.
• MLOps & Model Management:
• Establish and manage MLOps pipelines for continuous training, deployment, and evaluation of ML and GenAI models.
• Implement hallucination mitigation strategies, guardrail enforcement, and supervisor/observer patterns for real-time AI governance.
• Responsible AI Implementation:
• Drive Responsible AI (RAI) frameworks at scale, ensuring compliance, transparency, and explainability across all GenAI workflows.
• Develop audit-ready observability and explainable AI reporting for enterprise and regulated clients.
• Optimization & Cost Control:
• Design cost-efficient GenAI hybrid systems that balance deterministic and probabilistic approaches.
• Optimize LLM usage, context management, and API token costs without compromising model performance.

Required Skills & Qualifications

• Bachelor’s or Master’s degree in Computer Science, Machine Learning, Data Engineering, or a related field.
• 5+ years of hands-on experience in GCP AI/ML ecosystem (Vertex AI, Pub/Sub, BigTable, AlloyDB, etc.).
• Proven expertise with LangChain, LangGraph, or similar frameworks for orchestrating multiple GenAI agents.
• Deep understanding of prompt engineering, retrieval-augmented generation (RAG), and context window optimization.
• Strong background in MLOps, model observability, and LLM guardrail systems.
• Experience with event-driven architecture, real-time data streaming, and high-performance cloud solutions.
• Demonstrated success deploying Responsible AI and explainable AI practices in regulated sectors (FinTech, Healthcare, etc.).
• Experience balancing cost and performance in hybrid GenAI deployments (deterministic vs probabilistic pipelines).
• Strong coding skills in Python, Go, or TypeScript, with familiarity in API design, microservices, and container orchestration (Kubernetes).

Preferred Qualifications

• Prior experience with LangGraph and ReACT-style agent reasoning.
• Familiarity with RAG pipelines, vector databases, and semantic search.
• Exposure to GCP Cloud Run, Vertex Pipelines, or Dataflow.
• Knowledge of Responsible AI governance frameworks such as model cards, fairness checks, and explainability dashboards.