Build and operate production voice and LLM agents using LlamaIndex, LangChain, FastAPI, real-time speech pipelines, and telephony integrations. Responsibilities include RAG, tool calling, guardrails, concurrency, reliability engineering, testing, observability, latency optimization, and debugging customer calls. The role also involves collaborating with clients and FDEs, improving agents from call transcripts, and supporting regulated financial-services use cases.
This is a remote position.
Job Title: AI Engineer (Voice & Agentic Systems)
Location: Noida
Working Mode: Remote
Type: Full-time
Experience: 2+ Years (shipping LLM agents)
About the Company:
weya AI builds AI automations - Voice, video and WhatsApp agents that banks, lenders and insurers put in front of their customers. Our agents handle collections, onboarding, renewals, KYC follow-ups and support calls at scale, across India, the Middle East & Africa, Australia and the US. We're a small team of 11-15 people. Every engineer ships to production, talks to customers, and owns real outcomes. If an agent mishandles a loan call, it costs a client money and trust, so we build for reliability first.
About the Role:
You'll design, build and run the agents that talk to our clients' customers: LLM orchestration with LlamaIndex/LangChain, FastAPI services behind them, and real-time voice pipelines wired into telephony providers. You own an agent end to end, from the first prompt to the 10,000th concurrent call.
What You'll Do?
- Build agentic workflows with LlamaIndex and LangChain: tool calling, RAG over policy and loan documents, multi-step reasoning, and guardrails for regulated conversations.
- Design and run FastAPI services that serve agents in real time: async endpoints, WebSockets, webhooks, background tasks and clean API contracts.
- Build low-latency voice agents end to end: STT, LLM, TTS, voice activity detection, barge-in/interruption handling, and turn-taking.
- Integrate and maintain telephony providers (e.g. Twilio, Plivo, Exotel, Vonage, SIP trunks): inbound/outbound calls, call transfer, recordings, DTMF, and media streaming.
- Engineer for failure: provider outages, dropped calls, LLM timeouts, partial transcripts, retries and idempotency, so one bad dependency never takes down a campaign.
- Write tests that catch problems before clients do: unit and integration tests, simulated calls, load tests, and regression suites for agent behaviour.
- Instrument everything: latency per turn, call success rates, cost per call, and alerts that fire before a client notices.
- Work directly with FDEs and clients to turn real call transcripts into better agents.
Requirements
What We're Looking For? (Non-Negotiable)
- Agentic frameworks: shipped production agents with LlamaIndex and/or LangChain (or LangGraph), including tool use, memory and RAG. Not just notebooks.
- FastAPI: extensive experience building async Python services with FastAPI, Pydantic, WebSockets and background workers, under real traffic.
- Voice agents: built at least one voice agent that handled real customer calls, with hands-on work on STT/TTS providers (e.g. Deepgram, ElevenLabs, Azure, Google) and latency tuning.
- Telephony: integrated two or more telephony providers or SIP setups, and can explain how audio flows from a phone network to your code and back.
- Production mindset: you think about concurrency, rate limits, timeouts, retries and edge cases before writing the happy path, and you write tests for them.
- Debugging under pressure: comfortable reading logs, call recordings and traces to find why a call failed.
- Clear written English; able to explain a technical trade-off to a client.
Good to have (Bonus Points):
- Real-time voice frameworks such as LiveKit Agents or Vapi, or speech-to-speech models.
- Go for high-throughput services alongside Python.
- Multilingual voice work, especially Hindi, Hinglish, Arabic or other Indic languages.
- Experience in BFSI or other regulated domains: consent, call recording rules, PII handling, audit trails.
- LLM evaluation: automated scoring of agent conversations, prompt regression testing.
- WhatsApp Business API or video agent experience.
- Docker, Kubernetes, AWS/GCP, Redis, Postgres, and queues like Kafka or RabbitMQ.
Benefits
Get Real Experience on "What Success looks like?"
To apply: send your CV at [email protected], GitHub or a demo of a voice agent you built, and one paragraph
on the hardest telephony problem you've solved. Open question: application email or link.
Similar Jobs
.jpeg)
Artificial Intelligence • Hardware • Information Technology • Machine Learning
Leads high-volume semiconductor module and SSD manufacturing operations across assembly, testing, burn-in, inspection, labeling, and packing. Owns safety, quality, delivery, cost, productivity, capacity utilization, and workforce optimization for 24/7 operations. Directs supervisors and production teams, drives Lean, Six Sigma, Kaizen, AI, and smart manufacturing initiatives, and uses factory data to improve yield, OEE, cycle time, and labor productivity.
Top Skills:
Artificial IntelligenceKaizenLean ManufacturingMesOeePower BISAPSix SigmaSmart Manufacturing
Artificial Intelligence • Hardware • Information Technology • Machine Learning
Leads semiconductor test process engineering for Component Test manufacturing. Responsibilities include managing engineers, developing and qualifying processes, improving yield and quality, driving NPI readiness, establishing process controls, integrating equipment and technologies, applying statistical and digital analytics, and advancing Lean and Six Sigma initiatives. The role partners across engineering, manufacturing, quality, suppliers, and global sites while ensuring safety, compliance, operational efficiency, and talent development.
Top Skills:
Ai-Assisted AnalyticsAutomated Test Equipment (Ate)Design Of Experiments (Doe)JmpManufacturing AutomationMinitabPower BIPythonSemiconductor Test ManufacturingSQLStatistical Process Control (Spc)Tableau
Cloud • Information Technology • Security • Software
Lead cloud platform reliability across observability, FinOps, incident management, AI-driven automation, business continuity, and disaster recovery. Build production tooling in Go or Python across AWS and GCP, improve availability and recovery metrics, optimize cloud costs, design and test DR environments, and establish incident processes. Partner with engineering, finance, support, and leadership while mentoring teams and driving technical direction across the organization.
Top Skills:
AthenaAWSAws Compute OptimizerAws Cost And Usage Report (Cur)Aws Cost ExplorerBigQueryCloudabilityCloudhealthCommitted-Use DiscountsDatadogEbpfGCPGoGrafanaKubecostKubernetesLarge Language Models (Llms)LokiMimirOpentelemetryPrometheusPythonReserved InstancesSavings PlansTempoTerraformThanosVantage
What you need to know about the Pune Tech Scene
Once a far-out concept, AI is now a tangible force reshaping industries and economies worldwide. While its adoption will automate some roles, AI has created more jobs than it has displaced, with an expected 97 million new roles to be created in the coming years. This is especially true in cities like Pune, which is emerging as a hub for companies eager to leverage this technology to develop solutions that simplify and improve lives in sectors such as education, healthcare, finance, e-commerce and more.
