AI Engineer – Voice & Agentic Systems

Job not on LinkedIn

🕒 2 days ago

🇮🇳 India – Remote

⏰ Full Time

🟢 Junior

🟡 Mid-level

🤖 AI Engineer

🚫👨‍🎓 No degree required

👻 Ghost score 15%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

WEYA

WebsiteLinkedInAll Job Openings

2 - 10 employees

Founded 2009

⚡ Energy

🏗️ Construction

Energy • Construction

WEYA is a company that designs and delivers complete installations powered by renewable energy for heat and electricity production. Their projects focus on sustainable design, innovation, and intelligent, efficient control. With more than 50 references in a few years, WEYA is structured to provide long-term support for clients and implement renewable energy systems.

📋 Description

• Design, build, and run voice and agentic systems for clients' customers • Build agentic workflows with LlamaIndex and LangChain, including tool calling, RAG over policy and loan documents, multi-step reasoning, and guardrails for regulated conversations • Design and run FastAPI services with async endpoints, WebSockets, webhooks, background tasks, and clean API contracts • Build low-latency voice agents using STT, LLM, TTS, voice activity detection, barge-in/interruption handling, and turn-taking • Integrate and maintain telephony providers and SIP trunks for inbound/outbound calls, transfers, recordings, DTMF, and media streaming • Engineer resilience against provider outages, dropped calls, LLM timeouts, partial transcripts, retries, and idempotency issues • Write unit, integration, simulated-call, load, and agent-behavior regression tests • Instrument latency per turn, call success rates, cost per call, and alerts • Work directly with FDEs and clients to improve agents using real call transcripts • Own agents end to end from initial prompt through high-concurrency production calls

🎯 Requirements

• 2+ years of experience shipping LLM agents • Production experience with LlamaIndex and/or LangChain or LangGraph, including tool use, memory, and RAG • Extensive experience building async Python services with FastAPI, Pydantic, WebSockets, and background workers under real traffic • Built at least one voice agent handling real customer calls • Hands-on experience with STT/TTS providers such as Deepgram, ElevenLabs, Azure, or Google, including latency tuning • Integrated two or more telephony providers or SIP setups • Understanding of audio flow from a phone network to code and back • Production mindset covering concurrency, rate limits, timeouts, retries, and edge cases • Experience writing tests for production scenarios • Comfortable reading logs, call recordings, and traces to debug call failures • Clear written English • Able to explain technical trade-offs to clients

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume