Voice AI Infrastructure & Integration Engineer

About Firstsource:

Firstsource Solutions Limited, an RP-Sanjiv Goenka Group company (NSE: FSL, BSE: , Reuters: FISO.BO, Bloomberg: FSOL:IN), is a specialized global business process services partner, providing transformational solutions and services spanning the customer lifecycle across Healthcare, Banking and Financial Services, Communications, Media and Technology, Retail, and other diverse industries. With an established presence in the US, the UK, India, Mexico, Australia, South Africa, and the Philippines, we make it happen for our clients, solving their biggest challenges with hyper-focused, domain-centered teams and cutting-edge tech, data, and analytics. Our real-world practitioners work collaboratively to deliver future-focused outcomes.

Job Description:

Role Overview:

We are seeking an experienced Voice AI Infrastructure & Integration Engineer to own the platform reliability, observability, and telephony integration for our LLM-native voice agent. You will build the monitoring and tracing stack that gives full visibility into every call, own the call recording pipeline that satisfies FDCPA compliance, scale the orchestration runtime across container infrastructure, and integrate with telephony providers for SIP trunking, call routing, and audio stream handoff.

Key Responsibilities:

Observability, Logging & Monitoring

• Design and implement the full-stack observability pipeline using OpenTelemetry, Datadog, and ELK Stack — distributed traces, structured logs, and real-time metrics across every layer.
• Instrument the voice pipeline to emit per-turn telemetry: STT latency, LLM inference time, guardrail check duration, TTS first-chunk latency, and total round-trip time.
• Build alerting rules for latency SLA breaches, guardrail trigger rate spikes, STT/TTS error rates, and telephony drop rates.
• Create operational dashboards for real-time call volume, concurrent sessions, and per-vendor health.

Call Recording & Compliance

• Own the call recording pipeline: capture full-duplex audio and per-turn transcripts, store in S3 / Azure Blob with FDCPA-compliant retention.
• Integrate with the QA & audit portal (MaestroQA / EvaluAgent) for call playback, AI-assisted scoring, and compliance flag review.
• Ensure PCI-DSS compliance for stored audio: redact payment card segments before long-term storage.

CI/CD, Deployment & Scaling

• Build CI/CD pipelines for the voice agent codebase — orchestrator configs, system prompts, Markdown scripts, guardrail policies, and infrastructure-as-code.
• Containerize voice pipeline components using Docker and deploy on Kubernetes (EKS / AKS / GKE) with auto-scaling based on concurrent call volume.
• Implement blue-green and canary deployment strategies for zero-downtime rollouts.
• Manage session memory infrastructure (Redis / Upstash) with TTL, expiry, and failover for per-call state.

Telephony & Post-Call Integration

• Integrate with Twilio, Vonage, and Plivo for SIP trunking, call routing, and PCM / μ-law audio stream handoff.
• Configure calling windows, timezone management, contact frequency caps, and DNC enforcement at the telephony layer.
• Build post-call async jobs: CRM update, email confirmation, call summary generation, and payment gateway integration.
• Implement human escalation handoff — warm transfer with full conversation context passed to live agents.

Qualifications:

• 6–10 years in DevOps, SRE, or platform engineering, with 3+ years supporting real-time or voice/telephony systems.
• Bachelor’s or master’s in computer science, Information Systems, or related field.
• Track record building production observability stacks for distributed, latency-sensitive systems.
• Deep Kubernetes expertise — auto-scaling, GPU node management, multi-service deployments.
• Experience with telephony protocols (SIP, RTP, WebRTC) and at least one CPaaS provider.

Preferred:

• Experience in BPO, contact center, or financial services voice AI infrastructure.
• Hands-on with GPU infrastructure management (NVIDIA A100/H100, Triton Inference Server).
• Familiarity with voice pipeline orchestrators (Pipecat, LiveKit, Vocode) and their scaling patterns.
• Experience with per-call cost optimization for real-time AI systems.