Software Engineer (I)

Location: Mountain View, CA Salary: $65.00 USD Hourly - $75.00 USD Hourly Description:
COMPLETE JOB DESCRIPTION

Role Title: Software Engineer

Project Overview:

Responsibilities:
Agent Architecture & Development: Design and implement production-grade multi-agent AI solutions (including automated meta-agents and specialized orchestration agents) using modern frameworks optimized for enterprise cloud infrastructure.

Infrastructure & Asynchronous Pipelines: Architect and optimize large-scale ETL (Extract, Transform, Load) pipelines leveraging Kubernetes, container orchestration, and cloud-native AI pipelines to process high volumes of imagery data efficiently. Manage server configurations, microservices infrastructure, and deployment specifications for robust service operations.

Database & Schema Design: Design database scaling strategies using enterprise distributed SQL databases (e.g., globally distributed cloud databases) to manage and query massive geospatial and aerial imagery datasets. Structure and validate incoming imagery and maps metadata using typed schemas like Pydantic or Protocol Buffers.

Testing, Evaluation & QA: Build automated QA and validation pipelines using LLMs. Design and run rapid AI experiments, establish golden datasets, and execute rigorous evaluations for prompts and models (generating precision, recall, and F1 metrics).

Monitoring & Observability: Establish automated regression tests, tracing, and observability (using tools equivalent to LangSmith) across LLM agent runs and cloud infrastructure to monitor quality, latency, and cost. Build continuous evaluation frameworks to monitor deployed agents and enable Human-in-the-Loop (HITL) processes.

Role Qualifications
Minimum Qualifications:
Master's degree in Computer Science, a related technical field, or equivalent practical experience.
Professional experience in software development, including building large-scale, asynchronous data pipelines using Kubernetes, Docker, or industry equivalents like Celery, Airflow, or Kafka.
Extensive experience with Python programming and standard software engineering development practices.
Practical experience working with enterprise cloud services (AWS, Google Cloud Platform, or Azure) and containerized infrastructure orchestration.
Demonstrated proficiency in schema validation (e.g., Pydantic, Protobuf) and large-scale AI evaluations using precision/recall, F1 score, or LLM-as-a-judge methodologies.
Experience setting up golden datasets, designing rapid AI experiments, and deploying production AI agents using enterprise Agent Development Kits (ADKs) or AI SDKs.

Preferred Qualifications:
Experience working with generative AI and Large Language Models (LLMs), including expertise in advanced prompting techniques, fine-tuning, and evaluation.
Background in designing and deploying multi-agentic systems, autonomous architectures, and modern agentic orchestration frameworks (e.g., LangGraph, CrewAI, AutoGen, or LlamaIndex).
Experience with tool-calling protocols, including Model Context Protocol (MCP), API integrations, and function-calling schemas.
Experience with vector databases and vector search integrated with enterprise cloud databases for RAG architectures at scale.
Strong understanding of distributed systems and performance optimization in high-growth, high-volume data environments.

By providing your phone number, you consent to: (1) receive automated text messages and calls from the Judge Group, Inc. and its affiliates (collectively "Judge") to such phone number regarding job opportunities, your job application, and for other related purposes. Message & data rates apply and message frequency may vary. Consistent with Judge's Privacy Policy, information obtained from your consent will not be shared with third parties for marketing/promotional purposes. Reply STOP to opt out of receiving telephone calls and text messages from Judge and HELP for help.
Contact:
This job and many more are available through The Judge Group. Please apply with us today!