Software Engineer

SMS-Magic; Bengaluru; On-site; INR 1,200,000 - 2,000,000; Full time

Benefits offered by this job

Flexibility

Global environment

Hands-on AI tech

Impactful work

Job summary

Conversive is seeking a hands-on AI full-stack developer with ~2 years of experience to build and improve Voice AI agents, Chat AI assistants, and evaluation systems. You will design features across the stack, integrate LLMs, enable real-time streaming, and develop evaluation harnesses and datasets for continual improvement.

This early-career role emphasizes applied AI, production-ready conversational systems, and collaboration with cross-functional teams in an Agile environment.

Qualifications

• ~2 years of software development experience as a full-stack or backend-leaning engineer.
• Proficiency in Python with Flask or Django; writing automated tests (pytest).
• Frontend experience with React or Angular.
• Hands-on experience integrating LLM APIs (OpenAI, Claude, etc.).
• Understanding of core LLM concepts and embeddings/RAG.
• Knowledge of REST APIs and Postman usage.
• Exposure to MySQL or similar RDBMS.
• Comfortable in an Agile development environment.

Responsibilities

• Design, develop, unit test, and deploy full-stack features for Voice AI and Chat AI products.
• Integrate LLMs into conversational flows and tool-calling pipelines.
• Build and maintain Voice AI components: real-time audio streaming, STT/TTS integrations, and low-latency turn-taking.
• Develop Chat AI features including RAG, knowledge-base integration, and context management.
• Create AI evaluation and training tooling including test suites, automated evaluations, and dashboards.
• Curate and label datasets for fine-tuning and evaluation.
• Write clean, reusable code and participate in code reviews.
• Collaborate with Dev, QA, DevOps, Architects, and Product to deliver solutions.
• Work with support teams to resolve AI-related issues.
• Participate in Agile ceremonies and practice.
• Troubleshoot latency, accuracy, and reliability in large-scale environments.
• Share learnings on AI/LLM techniques with the team.
• Communicate clearly with technical and non-technical stakeholders.

Skills

Python

Flask

Django

React

REST APIs

LLM APIs

Automated testing

WebSockets

Postman

Docker

Redis

LangChain

Agile

Tools

Postman

WebSockets

Docker

Celery

Redis

LangChain

Job description

Role: Software Engineer Experience: ~2 years | Focus: Voice AI, Chat AI, and AI Evaluation & Training

Role: Software Engineer Experience: ~2 years | Focus: Voice AI, Chat AI, and AI Evaluation & Training

Position Overview

We are seeking a hands-on AI Full Stack Developer (~2 years of experience) to help us build and improve our AI applications - Voice AI agents, Chat AI assistants, and the systems we use to evaluate and train them. You will work across the stack: designing and developing application features, integrating LLMs and speech (STT/TTS) services, building real-time conversational flows, and creating the evaluation harnesses and datasets that make our AI measurably better over time. This is a high-impact role for an early-career engineer who is excited about applied AI and wants to ship production conversational systems.

Roles & Responsibilities

• Design, develop, unit test, and deploy full-stack features for Voice AI and Chat AI products.
• Integrate and orchestrate LLMs (e.g., Claude / GPT-class models) into conversational flows, prompts, and tool-calling / function-calling pipelines.
• Build and maintain Voice AI components - real-time audio streaming (WebSockets), speech-to-text and text-to-speech integrations, and low-latency turn-taking.
• Develop Chat AI features including RAG (retrieval-augmented generation), knowledge-base integration, and context/session management.
• Build AI evaluation and training tooling: prompt/response test suites, automated and LLM-as-judge evaluations, golden datasets, regression checks, and quality dashboards.
• Curate, label, and manage datasets used for fine-tuning, prompt optimization, and evaluation.
• Write reusable, extensible, and well-tested code; participate actively in code reviews.
• Collaborate across Dev, QA, DevOps, Architects, and Product to design and deliver solutions.
• Work with L2 and customer support teams to investigate and resolve AI-related customer issues.
• Participate in all scrum ceremonies and follow Agile development practices.
• Troubleshoot AI applications in a large-scale enterprise environment, including latency, accuracy, and reliability issues.
• Share learnings on AI/LLM techniques with the team and contribute to a strong learning culture.
• Communicate clearly in both written and verbal form, including with non-technical stakeholders.

What Will Qualify You for This Role?

Essential

• ~2 years of software development experience as a full-stack or backend-leaning engineer.
• Strong Python; experience with Flask or Django and writing automated tests (e.g., pytest / nosetest, coverage.py).
• Frontend experience with React or Angular.
• Hands-on experience integrating LLM APIs (OpenAI, Anthropic Claude, or similar) — prompt design, chat completions, and tool/function calling.
• Understanding of core LLM concepts: prompting, context windows, embeddings, RAG, and hallucination/quality tradeoffs.
• Solid knowledge of REST APIs; comfortable with Postman.
• Exposure to RDBMS such as MySQL.
• Ability to work effectively in an Agile framework.

Desired

• Experience building Voice AI: real-time audio over WebSockets, STT/TTS services (e.g., Deepgram, Whisper, ElevenLabs, Google/Azure Speech).
• Experience with AI evaluation frameworks, LLM-as-judge, or building custom eval/benchmark pipelines.
• Familiarity with vector databases (e.g., Pinecone, pgvector, Weaviate, Chroma) and embedding models.
• Exposure to AI orchestration / agent frameworks (LangChain, LlamaIndex, MCP, or similar).
• Experience with Gunicorn, Celery, RabbitMQ, and Redis.
• Exposure to AWS, Docker, and CI/CD (Jenkins).
• Exposure to NoSQL databases like MongoDB.
• Knowledge of Load Balancers (ALB) and Nginx.
• Experience with fine-tuning, dataset curation, or prompt optimization workflows.

What Working at Conversive Offers?

At Conversive, people growth is parallel to the company's growth, and our work culture supports our commitment to building a world-class AI-powered communications company. Our culture is built on high-performance teaming - where everyone can achieve their potential and contribute to building a better working world for our people and our clients.

We offer a sense of balance; we want our people to be active, healthy, and happy - not just in their jobs, but in their lives outside of work. Our competitive compensation package rewards you based on your performance and recognizes the value you bring to the business. We also do our best to make your time with us a rewarding learning experience that helps you grow as an individual.

Plus, We Offer

• The freedom and flexibility to handle your role in a way that's right for you.
• Exposure to a dynamic, growing global business environment.
• Direct, hands-on work with cutting-edge AI technology - LLMs, Voice AI, and conversational systems.
• Scope to showcase your analytical capabilities and make high-impact contributions to product and business teams.

About Conversive

Conversive is an AI-powered communications platform trusted by businesses around the world. We work with global customers across many industries including contact centers, financial services, higher education, retail, staffing, wellness, and more. Our customers range from small and mid-size businesses to large global enterprises.

Our commitment to every customer is to deliver the most advanced, simple-to-use AI-powered communications platform available, so they can focus on the personal touch that sets them apart from their competition.

Conversive is committed to inclusiveness, fairness, and accessibility. We encourage all qualified candidates to apply.