Dasceq is seeking a hands-on AI Engineer to architect and build a next-generation Agentic AI platform with voice, LLM, and data science capabilities.

About the Company

Dasceq is an innovative technology company building a next-generation Agentic AI platform that combines AI-powered conversations, predictive analytics, intelligent workflow automation, and business-system integrations. Their platform runs inbound and outbound AI agents across voice calls, SMS, and email, featuring automated dialing, CRM integrations, payment workflows, and campaign management. Initially serving accounts receivable and debt collection businesses, Dasceq is expanding into home services, field dispatch, sales, marketing, and customer support automation.

Role Overview

We are looking for a hands-on AI Engineer with strong Python programming skills and practical experience in building AI/ML applications, LLM-powered systems, or conversational AI solutions. The ideal candidate has personally architected and coded a voice or chat agent platform, understands how Agentic AI applications work internally, and can develop components, integrate APIs, write backend code, debug workflows, and contribute to building the AI platform from the ground up. We value candidates who have actually built agents, voice bots, and automation systems over those who used only existing no-code tools.

Key Responsibilities

1. Architect and build agentic voice platforms from scratch – Design and code end-to-end pipelines for AI calls: telephony, speech-to-text, LLM reasoning, text-to-speech, and call state management. Build agent orchestration with tool calling, multi-step workflows, conversation memory, guardrails, fallbacks, and human handoff. Optimize real-time performance: latency, barge-in and interruption handling, silence and turn detection, streaming.

2. Collections and inbound call workflows – Implement collections flows: identity verification, disclosures, negotiation, promise-to-pay, payment links, objection handling, dispute and callback handling. Build inbound flows for payments, account queries, scheduling and routing. Implement compliance controls such as call-time rules, consent, opt-out, DNC handling, call recording, and audit logs (with awareness of FDCPA, TCPA, Reg F for US markets).

3. Telephony, APIs and integrations – Integrate SIP, VoIP, and CPaaS providers (Twilio, Telnyx, Vonage, Plivo, Asterisk, FreeSWITCH or equivalent) and dialers, with SMS and email channels. Build REST APIs and webhooks to connect agents to CRM, payment gateways, scheduling, and collections systems. Build robust retry, idempotency, and error-handling logic.

4. LLM engineering and evaluation – Engineer prompts, structured outputs, and RAG pipelines for domain-specific conversations. Build evaluation frameworks: conversation quality scoring, hallucination and tool-failure testing, regression suites, and call-transcript analysis. Select, benchmark, and swap LLM, STT, and TTS vendors on cost, latency, and accuracy.

5. Data science and predictive analytics – Build and monitor models for propensity-to-pay, contactability, best time to call, recovery, and segmentation. Perform data cleaning, feature engineering, and model evaluation on payment and interaction data; support A/B tests and campaign analytics.

6. Cloud, deployment and production ownership – Deploy and run services on AWS (EC2, Lambda, S3, RDS, CloudWatch) using Docker and CI/CD. Own logging, monitoring, call-failure debugging, and performance tuning in production. Follow credential management, PII protection, and cloud-security practices.

7. Engineering practice and client delivery – Write clean, tested, documented Python code; use Git; review code and take part in design discussions. Join client requirement sessions with senior engineers; support UAT, demos, and onboarding; resolve client-reported issues.

Tech Stack

• Languages & Frameworks: Python (async programming, FastAPI/Flask, WebSockets, testing)
• LLM & Agent Frameworks: OpenAI, Anthropic, Gemini APIs, LangChain, LangGraph, custom orchestration
• Real-Time Voice: STT & TTS providers (Deepgram, AssemblyAI, Whisper, ElevenLabs, Cartesia, or similar), streaming audio, latency optimization
• Telephony: SIP, VoIP, Twilio, Telnyx, Vonage, Plivo, Asterisk, FreeSWITCH
• Cloud & DevOps: AWS (EC2, Lambda, S3, RDS, CloudWatch), Docker, Git, CI/CD
• Data & ML: SQL, Pandas, NumPy, scikit-learn, RAG, vector databases
• Optional/Good-to-have: Pipecat, LiveKit Agents, Vocode, Redis, Postgres, message queues, Kubernetes, observability tools, CRM integrations (Salesforce, HubSpot), payment gateways (Stripe, Razorpay, Authorize.net)

3-8 years of experience with strong Python, LLM engineering, real-time voice stack, telephony integration, and predictive modeling.

Hybrid work model in Noida/Gurugram; opportunity to lead AI platform development from scratch; competitive monthly salary.