Role: AI/ML Engineer - Agentic LLM Systems
Location: Hyderabad, In office
Type: Full time, Paid
Company Description
StepsAI creates intelligent AI Agents that provide instantaneous, human-like responses to customer inquiries, improving customer satisfaction and driving business growth. From FAQs and product recommendations to order tracking and support, our AI Agents offer seamless service 24/7 across platforms such as Websites, WhatsApp, Instagram, Shopify, WooCommerce, Slack, and internal knowledge bases. Our mission is to turn every customer conversation into actionable insights and revenue. StepsAI caters to diverse industries, from e-commerce to enterprise workflows, with a highly adaptive and versatile platform designed to handle complex customer interactions.
What You'll Do
AI/ML Development (Must have)
AI/ML Development (Must Have)
- Build production-grade multi-agent systems with robust error recovery, memory management, dynamic tool integration, and scalable orchestration
- Develop agentic workflows using frameworks such as LangChain, LangGraph, AutoGen, and LlamaIndex
- Design and enhance multimodal LLM pipelines integrating text, vision, audio, and structured data inputs
- Contribute to advanced RAG architectures including Graph-RAG, Agentic-RAG, and hybrid retrieval systems
- Optimize embeddings, reranking pipelines, and vector databases such as FAISS, Milvus, Pinecone, and Qdrant
- Work with orchestration and agent development platforms including Langflow, N8N, Agent Builder, and AgentSpace
- Standardize inter-agent communication and scalable AI execution pipelines for enterprise-grade deployments
- Improve retrieval accuracy, latency, observability, and production reliability across AI systems
Backend Development (Nice to have)
- API Development: Build robust REST APIs using FastAPI to serve ML models and agent workflows
- Frontend Integration: Develop responsive web interfaces using Next.js, TypeScript, and modern JavaScript
- Infrastructure & Deployment: Containerize applications with Docker and deploy using Kubernetes
- System Integration: Connect AI/ML services with databases, external APIs, and microservices architecture
- Performance Optimization: Ensure scalable, high-performance backend systems for real-time AI applications
Collaborative Growth
- Participate in full-stack development cycles from ML research to production deployment
Required Qualifications
AI/ML Expertise
- LLM Experience: Hands-on experience with transformer architectures (GPT, BERT, T5) and multimodal models through projects or coursework
- ML Frameworks: Proficiency with PyTorch/TensorFlow and AI frameworks like LangChain, Hugging Face, llamaindex, or AutoGen
- RAG & Agents: Experience building retrieval-augmented generation systems or multi-agent workflows (academic/personal projects welcome)
- Python for AI: Strong Python programming with focus on ML/AI libraries and data processing
Backend Development Expertise
- API Development: Experience with FastAPI, REST API design, and backend service architecture
- Frontend Skills: Proficiency in JavaScript, TypeScript, and Next.js for building modern web applications
- DevOps & Deployment: Hands-on experience with Docker containerization and basic Kubernetes knowledge
- Database & Integration: Understanding of databases, microservices, and API integration patterns
- Full-Stack Mindset: Ability to work across the entire stack from ML models to user interfaces
General Skills
- Problem Solving: Strong analytical and debugging skills across both AI/ML and software development domains
- Cloud Platforms: Familiarity with AWS/Azure/GCP and deployment practices
- Version Control: Proficient with Git and collaborative development workflows
- Communication: Clear technical communication and ability to work in cross-functional teams
Preferred Qualifications
- Open Source Contributions: Projects in AI/ML repositories or full-stack applications on GitHub
- Experience: AI/ML engineering, Backend development, or full-stack roles at tech companies
- Advanced AI Skills: Familiarity with prompt engineering, LLM fine-tuning, or multimodal AI research
- Modern Web Development: Experience with React ecosystem, state management, and modern JavaScript patterns
- Production Experience: Involvement in deploying ML models or web applications to production environments
Why Join Steps AI
- Build systems powering real-world AI products
- High ownership from day one
- Fast-moving engineering culture
- Opportunity to shape core platform architecture
