AI Support Engineer

About Max Val:
Max Val started as an IP services company in 2004, with a keen focus on efficiency, cost-effectiveness, and continuous improvement through metrics-based processes. Our focus on these core values led to the tech-enablement of our offerings even before this buzzword became an industry standard. Over the years, Max Val developed many internal applications to increase our quality and efficiency, and customer satisfaction.

As these systems grew and became more sophisticated, we have productized them and offered them to our clients. Today, Max Val serves over 600 clients across the full IP life cycle with the industry's leading products and services. Our 700 plus employees represent the most IP and tech-savvy individuals in the industry." At Max Val, we do the right things and innovate ceaselessly as a winning team to achieve customer success and employee success.

Job Responsibilities:

Pipeline Monitoring & Triage: actively monitor live Agentic workflows and scraping pipelines. Identify failures (e.g., stuck agents, failed scrapes, API timeouts), diagnose the root cause, and determine if it requires a quick fix or an escalation.
L1/L2 Code Maintenance:
Perform initial debugging of Python-based automation scripts. Fix minor logic bugs, dependency issues, or data formatting errors in the codebase.
Prompt Engineering & Adjustment:
Analyze LLM outputs for quality. Perform minor adjustments to system prompts or parameters (temperature, max tokens) to correct formatting or adherence issues without retraining models.
RAG Operations:
Assist in maintaining vector databases (Pinecone/Milvus). Handle re-indexing requests and verify that semantic search results are retrieving relevant context (checking for data staleness or embedding mismatches).
AWS Operational Support:
Manage the operational health of services on AWS (monitoring Cloud Watch logs, managing S3 buckets, checking Lambda execution states).
Issue Escalation:
Create detailed, technically rich bug reports for the Senior AI team when deep model fine-tuning or architectural changes are required (e.g., "Model consistently fails on X edge case due to loss function Y," rather than just "Model isn't working").

Requirements:
Required Skills
Scripting & Programming:
Proficient in Python (ability to read complex code, debug errors, and write maintenance scripts using Pandas/Num Py).
Cloud Operations:
Practical experience with AWS core services (specifically analyzing logs in Cloud Watch, managing storage in S3, and troubleshooting Lambda/EC2 basics).
AI/LLM Literacy:
Solid understanding of LLM concepts (Prompts, Tokens, Context Windows). Ability to troubleshoot "hallucinations" vs. "retrieval failures" in RAG systems.
Version Control:
Mandatory proficiency with GIT (pull requests, branching, and resolving merge conflicts).
Problem Solving: A detective mindset for tracing errors through distributed system logs.

Preferred Skills (Nice to Have)
Containerization:
Basic familiarity with Docker (building images, running containers, checking logs).
API Testing:
Experience using tools like Postman or cURL to test and validate AI model endpoints (FastAPI).
Visualization:
Experience creating simple dashboards (e.g., Streamlit or Grafana) to visualize system health or data throughput.

Basic Qualifications:

BS in Computer Science, Engineering, or a related field.
Experience in product development, preferably in SaaS and cloud environments.
1-3 years of experience in technical support, software maintenance, or junior development.
Experience or understanding of the Intellectual Property (IP) domain is highly desirable.

Website Link: