Software Engineer - AI Systems

Role: Software Engineer - AI Systems

Location: Hyderabad, In-office

Type: Full time, Paid

About StepsAI

Steps AI is building an agentic AI platform that powers AI agents for businesses across e-commerce, SaaS, healthcare, education, real estate, and financial services.

Our platform allows businesses to deploy AI agents across websites, messaging channels, internal tools, and customer workflows in minutes. These agents can answer questions, retrieve information, execute workflows, qualify leads, automate support, and integrate with business systems in real time.

We are building production-grade AI systems.

We are looking for a high-ownership engineer who wants to help build the core systems powering the next generation of AI products.

The Role

We're hiring a Senior Software Engineer - AI Systems to help build the infrastructure, orchestration, retrieval, and backend systems powering our agentic AI platform.

You will work across:

• AI runtimes
• orchestration systems
• retrieval infrastructure
• workflow engines
• integrations
• backend architecture
• streaming systems
• observability
• real-time AI execution pipelines

You will have significant ownership over technical direction and architecture decisions.

We move fast, ship frequently, and care deeply about execution quality.

What You'll Build

Agentic AI Infrastructure

• Build and evolve our AI agent runtime systems
• Design orchestration flows for multi-step reasoning and execution
• Implement tool calling, retries, state handling, and human escalation flows
• Build robust agent memory systems across sessions and conversations
• Improve response quality, latency, reliability, and observability

Retrieval & Knowledge Systems

• Build scalable RAG pipelines
• Work on embeddings, reranking, indexing, and retrieval quality
• Improve ingestion pipelines across websites, files, FAQs, and structured data
• Optimize recall, precision, and citation reliability

Workflow & Execution Systems

• Build long-running workflow systems for crawling, indexing, onboarding, and automation
• Design async pipelines, queues, retries, and distributed processing systems
• Build scalable event-driven backend architecture

Integrations & Platform Infrastructure

• Integrate with CRMs, helpdesks, commerce systems, messaging platforms, and internal tools
• Build backend APIs and AI-powered platform capabilities
• Work on real-time streaming infrastructure and execution pipelines
• Improve developer tooling, monitoring, and production debugging

Engineering Ownership

• Own systems end-to-end from architecture to production
• Write maintainable, scalable, production-grade code
• Participate in architecture reviews and technical planning
• Debug complex production issues across AI and backend systems
• Help set engineering standards as the team grows

Tech Stack

You do not need experience with everything below, but strong backend and systems fundamentals are required.

Core Technologies

• Python
• FastAPI
• TypeScript / Node.js
• PostgreSQL
• Redis
• Docker

AI / Agentic Stack

• LangGraph
• LangChain
• OpenAI
• Anthropic
• Gemini
• Vector databases (Qdrant, Pinecone, Milvus, Weaviate)

Infrastructure & Workflows

• Temporal
• Async processing systems
• Queue-based architectures
• Streaming systems
• AWS / GCP
• CI/CD pipelines

Observability

• Langfuse
• OpenTelemetry
• Production monitoring and tracing

What We're Looking For

Strong Backend & Systems Fundamentals

You understand scalable backend systems, distributed workflows, APIs, async processing, and production infrastructure.

High Ownership

You can independently take systems from idea → architecture → production.

Fast Execution

You move quickly, iterate aggressively, and care about shipping.

Deep Problem Solving

You debug deeply instead of patching symptoms.

Production Mindset

You think about reliability, observability, failure handling, latency, and scalability from day one.

AI Curiosity

You are excited about agentic systems, orchestration, retrieval, and AI infrastructure.

Strong Plus

• Production experience with AI agents or RAG systems
• Experience with LangGraph or workflow orchestration systems
• LLM observability and evaluation
• Multi-agent architectures
• Real-time streaming systems
• Advanced retrieval systems
• Web crawling and ingestion infrastructure
• Open-source contributions
• Startup experience

Qualifications

• 2+ years of strong software engineering experience
• Demonstrated ability to build and ship production systems
• Strong programming skills in Python and/or TypeScript
• Ability to work in a fast-paced startup environment
• On-site in Hyderabad, India

Why Join Steps AI

• Build cutting-edge AI systems used by real businesses
• High ownership from day one
• Fast-moving engineering culture
• Opportunity to shape core platform architecture
• Competitive compensation