Senior AI Technical Architect

Anvaya Solutions•Sacramento, CA

20h•Hybrid

About The Position

This is a 1-year base term contract position with the potential for extension based on remaining contract hours. The role can be performed remotely or onsite in the Sacramento, CA area. The position requires extensive experience in AI-Enhanced Software Engineering, Advanced Large Language Model (LLM) and Agentic System Design, Predictive Log and Telemetry Intelligence, and AI Quality Guardrails.

Requirements

A minimum of five (5) years of experience in AI-Enhanced Software Engineering.
Advanced skills in Python and strong knowledge of backend architecture.
Hands-on experience using AI coding assistants (such as GitHub Copilot or Cursor).
Proven ability to set up and manage automated Continuous Integration/Continuous Deployment (CI/CD) pipelines.
Experience implementing AI-driven quality checks and generating unit tests within CI/CD workflows.
A minimum of three (3) years of experience in Advanced Large Language Model (LLM) and Agentic System Design.
Hands-on experience designing multi-agent workflows that coordinate tasks across different AI agents.
Building and optimizing Retrieval Augmented Generation (RAG) pipelines, including improving vector database search for faster and more accurate results.
Applying Chain of Thought reasoning techniques to support complex tasks in the Software Development Lifecycle (SDLC).
Using frameworks such as LangGraph, CrewAI, or AutoGPT to automate end-to-end development processes.
A minimum of three (3) years of experience in Predictive Log and Telemetry Intelligence.
Working with large, unstructured datasets such as system logs, distributed tracers, and heap dumps.
Designing solutions that can identify patterns and predict issues before they impact system performance.
Applying AI techniques to improve log analysis and telemetry monitoring for faster troubleshooting.
A minimum of two (2) years of experience in AI Quality Guardrails.
Building Human-in-the-Loop systems where humans review and validate AI outputs for accuracy and safety.
Creating automated evaluation frameworks such as Retrieval Augmented Generation Assessment (RAGAS) and Generative Evaluation (G-Eval) to measure AI performance.
Implementing safeguards to prevent hallucinations (incorrect or fabricated outputs) in technical results.
Designing strategies to mitigate prompt injection risks for autonomous AI agents, ensuring secure and reliable operations.

Responsibilities

Design and implement AI-Enhanced Software Engineering solutions.
Set up and manage automated Continuous Integration/Continuous Deployment (CI/CD) pipelines.
Implement AI-driven quality checks and generate unit tests within CI/CD workflows.
Design Advanced Large Language Model (LLM) and Agentic Systems.
Design multi-agent workflows for task coordination.
Build and optimize Retrieval Augmented Generation (RAG) pipelines.
Apply Chain of Thought reasoning techniques within the Software Development Lifecycle (SDLC).
Automate end-to-end development processes using frameworks like LangGraph, CrewAI, or AutoGPT.
Design Predictive Log and Telemetry Intelligence solutions.
Identify patterns and predict issues in system performance using large, unstructured datasets.
Apply AI techniques to improve log analysis and telemetry monitoring.
Build AI Quality Guardrails, including Human-in-the-Loop systems.
Create automated evaluation frameworks for AI performance.
Implement safeguards against hallucinations in technical results.
Design strategies to mitigate prompt injection risks for autonomous AI agents.