AI Software Engineer

Practice By Numbers, Inc.; Gurugram District; On-site; INR 3,000,000 - 4,200,000; Full time

Job summary

Practice by Numbers (PBN) in Gurugram, India, is seeking an AI Software Engineer to own backend and AI features end-to-end. You will build production-grade microservices, APIs, and multi-turn conversational AI with HIPAA-compliant data handling, latency-aware design, and robust integration with dental practice systems.

The role requires 2–6 years of experience, strong Python and FastAPI/Django skills, and hands-on work with LLMs, prompts, and tool calls.

Qualifications

• 2–6 years of professional software development experience.
• Hands-on backend services and production APIs.
• Experience with LLM-based applications and prompt design.

Responsibilities

• Build and maintain backend services and RESTful APIs in Python.
• Develop AI-driven conversation flows and tool calling.
• Integrate with practice management systems and HIPAA-compliant data handling.
• Collaborate with PM and QA; write tests and ensure reliability.

Skills

Python

FastAPI

PostgreSQL

Redis

Asynchronous Python

REST APIs

CI/CD

AWS / GCP / Azure

LLM-based apps

Prompt design

Tools

Twilio

Vonage

Deepgram / STT

ElevenLabs

AssemblyAI

LangChain

LlamaIndex

Celery

AWS SQS

Job description

## AI Software Engineer## Practice by Numbers (PBN) | Gurugram, India Scope: AI / Conversational Products & Backend Services**About Practice by Numbers**Practice by Numbers is a dental practice management SaaS platform serving over 1,500 practices acrossNorth America — practice management software, VOIP, payment processing, and analytics. We're nowexpanding into AI-powered automation, building conversational AI products that change how practicesinteract with their patients.**About the Role**We’re looking for a Software Engineer with strong, hands-on experience in both backend productengineering and modern AI systems. The ideal candidate can design and build reliable, production-gradeservices while also developing, integrating, and deploying AI-powered capabilities. As this is a singleopening on a small team, we need someone who can take end-to-end ownership across both areas andcontribute independently throughout the product development lifecycle.You'll work on our AI Receptionist — a multi-channel conversational AI (voice, SMS, web chat) for dentalpractices — and the backend services, APIs, and integrations behind it. Hands-on IC role: you ownfeatures end to end, including their production behaviour. Real patient-facing traffic under HIPAAconstraints, where correctness and latency both matter.**Reports to:** Lead Engineer — AI**Location:** Gurugram, India — this role is open in Gurugram only**Work Mode:** In-office**Working Hours:** Primarily IST (10 AM – 5 PM), with some evening overlap with US teams (until 9–11 PM IST) as needed**What You'll Do****Backend**● Build and maintain backend services and RESTful APIs in Python (FastAPI / Django)● Design schemas and write efficient PostgreSQL queries; use Redis for caching and session state● Work with async and event-driven patterns — queues, webhooks, WebSockets, background workers● Own the operational side: logging, metrics, alerting, debugging production issues● Write unit and integration tests for the business logic you ship**AI & LLM**● Build and iterate on LLM-driven conversation flows: tool calling, multi-turn state, context handling● Write and refine prompts for specific use cases, and measure the impact of changes● Build guardrails for patient-facing interactions — no medical advice, no unverified data disclosure● Work with RAG and knowledge-base retrieval for practice-specific questions● Contribute to evaluation and regression testing so AI quality doesn't drift between releases● Balance response quality, latency, and cost across LLM and voice vendors**Integrations & Data**● Integrate with practice management systems (Dentrix, Open Dental, Eaglesoft) and internal PBN APIs● Implement secure auth flows, including OTP-based patient verification● Follow HIPAA-compliant practices across data handling, logging, and storage Collaboration● Work with Product Management to turn requirements into working software, surfacing edge cases early● Participate in sprint planning, standups, code reviews, and product reviews● Document what you build; collaborate across time zones with US-based stakeholders**Required Qualifications****Experience**● 2–6 years of professional software development experience● Hands-on experience building backend services and APIs that ran in production● Practical experience with LLM-based applications (GPT-4/4o, Claude, or similar) — prompt design, tool calling, handling model output in real systems. Substantial personal or open-source work counts; tutorial-level does not.● Experience debugging and improving a system after it shipped**Technical Skills**● Strong Python — our primary language across AI and backend● APIs: RESTful services, webhooks, third-party integrations; FastAPI or Django preferred● Databases: PostgreSQL — schema design, indexing, query performance; Redis or similar● Async Python (asyncio) and event-driven architectures● Cloud: working knowledge of AWS (or GCP/Azure) — compute, storage, managed DBs, queues● Version control, code review, and CI/CD as normal parts of your workflow**AI Domain Understanding**● Clear view of what LLMs can and cannot do reliably, and how that shapes product design● Prompt engineering and conversation design for multi-turn interactions● Familiarity with RAG and agentic patterns — tool use, orchestration● Some experience evaluating and monitoring LLM systems● Awareness of token cost and latency trade-offs**Soft Skills**● Comfort with ambiguity — you can make a reasonable call and explain it● Clear communication with technical and non-technical stakeholders● Able to drive your own work to completion without close supervision● Comfortable with a fast pace and evolving requirements● Willing to work in-office in Gurugram and overlap with US hours when needed**Preferred Experience & Skills**● Conversational AI — chatbots, voice assistants, or IVR● Voice/telephony (Twilio, Vonage) or STT/TTS APIs (Deepgram, ElevenLabs, AssemblyAI)● LLM orchestration frameworks (LangChain, LlamaIndex) — or a considered view on skipping them● Healthcare / HIPAA compliance knowledge● Observability tools (Datadog, New Relic, Sentry, Papertrail)● Celery or similar task queues; AWS SQS or equivalent● SaaS or B2B product company background; multi-tenant architecture● Open-source contributionsReady to apply?