AI Software Engineer (Backend, Agentic & Voice AI)

Steps AI, Inc.; Hyderabad; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Steps AI is hiring a backend/full-stack engineer to join our core engineering team in Hyderabad. You will build and ship features powering real customer-facing AI agents and voice capabilities.

You’ll work primarily on Python (FastAPI) and TypeScript (NestJS), integrate LLM providers, design robust APIs, and contribute to retrieval pipelines and streaming responses. This role offers direct access to the founders, a fast learning curve on production-grade voice AI, and the opportunity to shape a

Qualifications

• 1–3 years of professional backend or full-stack experience.
• Strong Python (FastAPI) and working knowledge of Node.js/TypeScript is a plus.
• Hands-on experience with LLM APIs and GenAI projects you can demo.
• Familiarity with LangChain, LangGraph or a similar agent framework.
• Experience with a vector database (Pinecone, Qdrant, Milvus or Weaviate).
• PostgreSQL and REST API design.
• Git, Docker, and basic cloud (AWS/GCP) knowledge.

Responsibilities

• Build and improve AI agents: tool calling, conversation state, routing, escalation to humans, and streaming responses
• Build real-time voice AI agents: speech-to-text, LLM reasoning and text-to-speech pipelines, with low latency and natural turn-taking
• Integrate LLM providers with fallbacks and cost/latency tradeoffs
• Build retrieval (RAG) pipelines: ingestion, chunking, embeddings, hybrid search and reranking
• Develop backend APIs in Python (FastAPI) and/or TypeScript (NestJS) for agents, workspaces, integrations and billing
• Build integrations with WhatsApp, Instagram, Shopify, WooCommerce, CRMs, helpdesk tools and telephony providers
• Work on long-running workflows such as crawling, document parsing and scheduled jobs
• Contribute to the React/Next.js dashboard and embeddable chat/voice widget when needed
• Monitor what you ship: token usage, latency, answer quality, call quality and errors

Skills

Python (FastAPI)

Node.js/TypeScript

LLM APIs

LangChain/LangGraph

Vector DB

PostgreSQL

REST API design

Git & Docker

Cloud (AWS/GCP)

Education

B.Tech / M.Tech / MS in CS

Tools

Docker

FastAPI

NestJS

PostgreSQL

LangChain

Pinecone

Weaviate

AWS

GCP

Job description

Steps AI builds customer-facing AI agents for e-commerce, SaaS, healthcare, real estate, EdTech and financial services. Our agents go live in under five minutes from a single URL. They learn the business from websites, documents, FAQs and product catalogs, and work across web, WhatsApp, Instagram and other channels.

We’re now expanding into voice, so our agents can talk to customers as well as chat with them. We’re profitable, growing fast, and ship production AI to customers every week.

The Role

You’ll join our core engineering team and work directly with the founders to build and ship features used by real customers. You’ll mainly work on the AI and backend side, including our new voice agents, with exposure to the frontend as you grow.

What You’ll Work On

• Build and improve AI agents: tool calling, conversation state, routing, escalation to humans, and streaming responses
• Build real-time voice AI agents: speech-to-text, LLM reasoning and text-to-speech pipelines, with low latency and natural turn-taking
• Integrate LLM providers (OpenAI, Anthropic, Gemini) with fallbacks and cost/latency tradeoffs
• Build retrieval (RAG) pipelines: ingestion, chunking, embeddings, hybrid search and reranking
• Develop backend APIs in Python (FastAPI) and/or TypeScript (NestJS) for agents, workspaces, integrations and billing
• Build integrations with WhatsApp, Instagram, Shopify, WooCommerce, CRMs, helpdesk tools and telephony providers
• Work on long-running workflows such as crawling, document parsing and scheduled jobs
• Contribute to the React/Next.js dashboard and embeddable chat/voice widget when needed
• Monitor what you ship: token usage, latency, answer quality, call quality and errors

Must-Have Skills

• 1-3 years of professional experience building backend or full-stack applications
• Strong Python (FastAPI, async, Pydantic); working knowledge of Node.js/TypeScript is a plus
• Hands-on experience with LLM APIs and at least one GenAI project (RAG, chatbot, agent or voice bot) that you can demo
• Familiarity with LangChain, LangGraph or a similar agent framework
• Experience with a vector database (Pinecone, Qdrant, Milvus or Weaviate)
• PostgreSQL and REST API design
• Git, Docker, and basic cloud (AWS/GCP) knowledge

Good to Have

• Voice AI experience: STT/TTS providers (Deepgram, ElevenLabs, Whisper, Cartesia), real-time frameworks (LiveKit, Pipecat) or telephony (Twilio, Exotel, Plivo)
• Knowledge of WebSockets, WebRTC or audio streaming
• React / Next.js, Tailwind
• WhatsApp Business API, Shopify or other third-party API integrations
• Workflow tools (Temporal, Airflow, Celery)
• LLM observability (Langfuse, OpenTelemetry)
• Open-source contributions, side projects or hackathon work in GenAI

Who You Are

• You ship fast and learn faster
• You can read code, trace a bug across services and fix it yourself
• You turn business requirements into working features without much hand-holding
• You care about reliability, including retries, idempotency and guardrails
• You’re excited to work on a new product area (voice) from the early stages

Qualifications

• B.Tech / M.Tech / MS in CS, AI/ML or a related field (or equivalent practical experience)
• Must be able to work on-site in Hyderabad

What We Offer

• Direct access to the founders and real ownership of what you build
• A fast learning curve on production agentic and voice AI