AI/ML Engineer

Anvaya Solutions•Sacramento, CA

About The Position

This role involves AI-Driven Core Development, Large Language Model (LLM) integration and Prompt Engineering, Technical Data Classification, and building AI-powered tools and extensions. The position has a 1-year base term with the option to extend for two additional years.

Requirements

Minimum three (3) years of experience in AI-Driven Core Development, including at least two (2) of the following: Strong Python skills with proven experience building scalable applications. Ability to use Large Language Models (LLMs) to refactor code and generate documentation. Experience maintaining high-quality Git (distributed version control) workflows in a collaborative team environment.
Minimum two (2) years of experience in Large Language Model (LLM) integration and Prompt Engineering, including at least three (3) of the following: Implementing Retrieval Augmented Generation (RAG) features in real applications to ground model outputs in authoritative data. Designing, testing, and iterating prompts for technical tasks (e.g., coding assistance, test generation, documentation). Proficiency with LangChain or an equivalent framework (e.g., Llamaindex, Haystack) to orchestrate LLM workflows. Integrating LLMs with external data sources such as Jira (issue/project tracking), GitHub (code hosting/collaboration), and internal knowledge wikis, including authentication and permission handling. Establishing monitoring and guardrails to track prompt effectiveness and ensure reliable, reproducible results.
Minimum two (2) years of experience in Technical Data Classification, including at least three (3) of the following: Using Artificial Intelligence (AI) and Machine Learning (ML) techniques to categorize and summarize technical data. Building classifiers that can accurately distinguish between critical system errors and routine log outputs. Designing solutions that prioritize developer alerts based on severity and impact. Applying data preprocessing and feature engineering to improve classification accuracy. Implementing monitoring and validation processes to ensure classifier reliability over time.
Minimum two (2) years of experience building AI-powered tools and extensions. This includes creating custom productivity tools, such as Visual Studio Code (VS Code) extensions or command-line utilities, that use Large Language Model (LLM) APIs to provide developers with smart, context-aware assistance.

Nice To Haves

Experience with the Salesforce development lifecycle and using Artificial Intelligence to automate manual testing or improve Apex (Salesforce programming language) code quality.
Salesforce Developer Experience.
Experience with basic computer vision for UI/UX (User Interface/User Experience) analysis and automated frontend testing.
Experience with Large Language Model evaluation techniques to ensure generated code and technical summaries are accurate and safe for production use (e.g., prompt-quality checks, output validation, safety/guardrail methods).