Senior AI Engineer

Company Description

TaloTrace is an AI-powered QA platform that autonomously tests web and mobile applications, discovers issues, and delivers evidence-backed findings your engineering team can act on immediately.

Unlike traditional automation tools that stop at pass or fail, TaloTrace provides a complete Trace for every issue: recorded video, logs, reproduction steps, severity, and supporting evidence.

Job Description

We are looking for an Senior AI Engineer with a primary focus on:

• FastAPI, Firebase, and GCP tools for backend services built with Python
• Agentic and multi-agent LLM systems that support Growtrics’ learning and operations workflows
• Backend systems that are automation-friendly, test-friendly, and reliable enough for production use

The candidate must be comfortable working with:

• Multi-agentic systems around LLM providers such as OpenAI, Claude, Gemini, and Perplexity, built mainly with Python
• Agentic coding harnesses such as Claude Code, Codex, Cursor, or equivalent tools as part of the actual engineering workflow
• Backend workflows involving jobs, state machines, retries, data validation, evaluation loops, and human review

Examples of projects you could be responsible for:

• Creating a multi-agent system to generate educational videos for users, where coding harnesses like Claude Code or Codex are used to iteratively refine the output autonomously
• Building backend workflows for automatic grading, feedback generation, learning path optimization, and AI-assisted review
• Designing services that coordinate LLM calls, tools, queues, data stores, and human approval steps
• Creating automation and testing systems that use LLMs or agents to simulate user behavior, reproduce bugs, and detect failures

You would also be expected to tackle common engineering problems such as bug fixes,

backend feature upgrades, integrations, test improvements, and operational reliability work.

Skillsets

Soft Skills

Above technical skills, these soft skills and values are a must.

• Independence, Initiative and Learning: In a rapidly evolving AI-assisted coding environment, we extremely value the ability to learn new technologies and spearhead initiatives independently. You must solve problems logically and quickly by yourself. This includes high mastery over power tools such as ChatGPT, Perplexity, Claude Code, Codex, Cursor, and similar agentic coding harnesses.
• Communication: The ability to communicate one’s own ideas effectively in English. If there is a problem with the codebase, architecture, data, or project direction, we prefer our team members to raise it promptly.
• Creativity: New and creative ideas that streamline business processes, feature pipelines, grading workflows, or engineering automation are welcome.
• Agility: Project requirements might be ever changing. Team members should be able to follow changing plans with good spirit.
• Result Oriented: Everyone is assessed based on the quality and timeliness of their output.

Technical Skills

Fast learners with some experience will be prioritized over slow learners with more experience. These are some of the skill sets that we are looking for.

• Strong hands-on experience, or clear depth, building agentic and multi-agent LLM pipelines in Python
• Required proficiency using agentic coding harnesses such as Claude Code, Codex, Cursor, or equivalent tools to do real implementation work
• Experience working with multiple LLM providers such as OpenAI, Claude, Gemini, and Perplexity
• Familiarity with agent orchestration frameworks, tool-calling, memory, and evaluation loops
• 1+ year of experience working with agentic LLM systems in production or production-like environments
• 4-8 years of experience building backend applications with FastAPI, with Flask or Django also acceptable
• Experience designing backend systems that are automation- and test-friendly
• Experience with Firebase, GCP tools, Cloud Run, Firestore, Pub/Sub, Cloud Tasks, or similar cloud services
• Strong testing mindset with high standards for test quality, documentation, observability, and debuggability
• Experience using LLMs to simulate user behavior, generate tests, detect bugs, and reproduce failures
• Comfortable working across QA systems, feature development, integrations, operations, and bug fixing

Experience with the following is preferred:

• Vector databases, such as Qdrant, Weaviate, or Milvus
• Graph …