Artificial Intelligence Engineer

Recrew AI; Gurugram District; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Recrew AI in Gurugram is seeking a backend software engineer focused on AI-driven dental healthcare solutions. You will own end-to-end development of the AI Receptionist, building production-grade Python services, LLM-driven flows, and integrations with dental management systems in a HIPAA-constrained environment.

Responsibilities include designing RESTful APIs, optimizing PostgreSQL, handling async patterns, and ensuring robust observability.

Qualifications

• 2–6 years of professional software development experience with backend services and APIs running in production.
• Proficient in Python with FastAPI or Django for RESTful service development.
• PostgreSQL — schema design, indexing, and query performance; Redis or equivalent for caching and session state.
• Practical, production-level experience with LLM-based applications (GPT-4/3.5, Claude, or similar).
• Async Python (asyncio) and event-driven architectures — queues, webhooks, WebSockets.
• Working knowledge of AWS (or GCP/Azure).
• Understanding of LLM capabilities and prompt engineering for multi-turn interactions, token costs.

Responsibilities

• Build and maintain backend services and RESTful APIs in Python (FastAPI or Django).
• Develop LLM-driven conversation flows with multi-turn state management and guardrails.
• Implement asynchronous patterns: queues, webhooks, WebSockets, and background workers.
• Integrate with dental practice management systems and internal APIs with HIPAA-compliant auth flows.
• Own logging, metrics, alerting, and debugging production issues.
• Write and refine prompts for specific use cases and measure LLm performance.

Skills

Python

FastAPI/Django

PostgreSQL

Redis

LLM prompts

Asyncio

AWS/GCP/Azure

HIPAA understanding

Tools

Dentrix

Open Dental

Eaglesoft

Twilio

LangChain

LlamaIndex

Job description

Function: Software Engineering / AI & Backend Development

Location: Gurugram

Type: Full-time

Industry: AI, Medical SaaS, Dental Healthcare Technology

About Company

The company builds medical AI SaaS for the U.S. dental market.

Its all-in-one platform serves 1,500+ dental practices across North America. It unifies analytics, scheduling, communications, payments, and marketing automation.

The platform automates admin work and gives teams real-time visibility into revenue and retention. Founded in 2015 by a practicing dentist, a data strategist, and a PhD technologist.

The team of ~88 moves fast, ships real value, and operates with high ownership.

Position Overview

This role sits at the intersection of backend product engineering and modern AI systems. You will own end-to-end development of the company's AI Receptionist — a multi-channel conversational AI (voice, SMS, web chat) built for dental practices. You will design and ship production-grade Python services, LLM-driven conversation flows, and integrations with dental practice management systems, all under HIPAA constraints where both correctness and latency matter. This is a hands-on individual contributor role with direct patient-facing traffic and full ownership of features through their production lifecycle.

Role & Responsibilities

• Build and maintain backend services and RESTful APIs in Python (FastAPI or Django), including schema design, efficient PostgreSQL queries, and Redis-based caching and session state
• Develop and iterate on LLM-driven conversation flows — tool calling, multi-turn state management, context handling — and build guardrails for patient-facing interactions to prevent medical advice or unverified data disclosure
• Implement async and event-driven patterns: queues, webhooks, WebSockets, and background workers
• Integrate with dental practice management systems (Dentrix, Open Dental, Eaglesoft) and internal company APIs, including OTP-based patient verification and HIPAA-compliant auth flows
• Own the operational side of what you ship: logging, metrics, alerting, and debugging production issues
• Write and refine prompts for specific use cases, measure the impact of changes, and evaluate LLM system performance in production
• Collaborate with Product Management and US-based stakeholders across time zones — surfacing edge cases early, participating in sprint planning, code reviews, and documenting what you build

Must Have Criteria

• 2-6 years of professional software development experience with backend services and APIs running in production
• Strong Python proficiency; FastAPI or Django for RESTful service development
• PostgreSQL — schema design, indexing, and query performance; Redis or equivalent for caching and session state
• Practical, production-level experience with LLM-based applications (GPT-4/3.5, Claude, or similar) — prompt design, tool calling, and handling model output in real systems (substantial personal or open-source work counts; tutorial-level does not)
• Async Python (asyncio) and event-driven architectures — queues, webhooks, WebSockets
• Working knowledge of AWS (or GCP/Azure) — compute, storage, managed databases, queues
• Clear understanding of LLM capabilities and limitations, including prompt engineering for multi-turn interactions, RAG, agentic patterns, and token cost/latency trade-offs

Nice to Have

• Conversational AI experience — chatbots, voice assistants, or IVR systems
• Voice/telephony integrations (Twilio, Vonage) or STT/TTS APIs (Deepgram, ElevenLabs, AssemblyAI)
• LLM orchestration frameworks such as LangChain or LlamaIndex — or a considered rationale for avoiding them
• Healthcare or HIPAA compliance knowledge
• Observability tooling (Datadog, New Relic, Sentry, Papertrail) and task queues (Celery, AWS SQS or equivalent)
• SaaS or B2B product company background with multi-tenant architecture experience

What We Offer

• End-to-end ownership of patient-facing AI products used by 1,500+ dental practices across North America
• Direct impact on a fast-growing AI product line in a large, under-digitized healthcare vertical
• Tight, cross-functional team with high autonomy and fast shipping cycles
• Growth and development support in a mission-driven, execution-oriented environment