AI Engineer
YAL.ai (company site, opens in a new tab)HyderabadOn-siteDirect career pageEst. 18–35 LPA
Posted 15h ago
Reach people at YAL.ai
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at YAL.ai you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Design, build, and maintain LLM-based AI agents that handle multi-step business tasks across voice, chat, and back-office channels with tool integration and human approval where necessary.
- Own and develop evaluation systems including golden test sets, trajectory and simulated-caller evaluations to gate releases and ensure task success, tool call correctness, and compliance.
- Build and operate back-end services for AI agents ensuring latency under 1 second for voice responses, robust error handling, audit trails, security, and scalable production deployments.
Minimum Requirements
- Strong proficiency in Python backend development including APIs, asyncio, WebSockets, error handling, and automated testing.
- Hands-on experience shipping LLM agents beyond demos, with expertise in tool calling, state management, RAG, and failure handling in real workflows.
- Working knowledge of real-time voice tech stack (streaming ASR, TTS, VAD, turn-taking) and latency vs accuracy trade-offs.
- Bachelor’s degree in a technical field or equivalent practical experience with demonstrable delivered work.
Ideal Candidate Profile
- Experience designing complex autonomous or semi-autonomous AI agent workflows balancing fixed workflows and multi-agent systems with safe design including permissions and guardrails.
- Skilled in building and running evaluations for LLM agents with detailed metrics and regression tracking affecting CI releases.
- Able to debug distributed AI agent systems using logs, tracing, and recorded sessions and maintain production voice/chat agents with integration to telephony or WebRTC platforms.