Job Title

Job Title: Senior AI/ML Engineer – Agentic LLM SystemsLocation: RemoteJob Type: Paid, Full-TimeImportant Note: Only Apply if you have Experience: ≥ 3 years in ML/AI production level engineering and deployment, with ≥ 1.5 years specifically building and deploying LLM-based systems, agentic tools, function, and RAG pipelines.Who We AreSteps AI is a cutting-edge AI company redefining how enterprises retrieve and act on data through autonomous, agent-powered workflows. Our platform leverages the latest in multi-agent orchestration, RAG, and generative AI to deliver real-time, contextual insights. As we scale our product suite, we’re seeking an experienced AI/ML engineer to lead the design and delivery of next-generation agentic LLM solutions.What You’ll Do● Architect & Lead Multi-Agent Frameworks ○ Design production-grade agent ecosystems featuring robust error-recovery, long-term memory, and dynamic tool integration ○ Standardize inter-agent communication via Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocols● Build Multimodal LLM Solutions ○ Integrate vision, audio, and structured data inputs into unified LLM pipelines ○ Implement cross-modal retrieval strategies and fine-tune multimodal encoder–decoder models● Drive RAG Pipeline Excellence ○ Lead the design of Graph-RAG, Agentic-RAG, and hybrid retrieval architectures for high-accuracy knowledge access ○ Optimize embedding stores, vector databases (FAISS, Milvus), and reranking strategies● Advance Agent-Building Tooling ○ Champion frameworks such as N8N, Langraph, Langflow, Agent Builder and AgentSpace for rapid agent prototyping and governance ○ Extend and harden orchestration libraries (LangChain Agents, AutoGen, LlamaIndex) for enterprise use. ○ Multi-Agent Systems: Develop LLM-based agents for dynamic tasks using orchestration frameworks.● Mentor & Evangelize Best Practices ○ Guide junior engineers on SOLID design, DRY/YAGNI coding, CI/CD pipelines, and peer code reviews ○ Present architecture reviews, design patterns, and performance benchmarks at team tech-talksMust-Have Qualifications● Experience: ≥ 3 years in ML/AI engineering, with ≥ 2 years specifically building and deploying LLM-based systems and RAG pipelines● We will critically evaluate your problem statement understanding, system design, theoretical understanding of LLM techniques/models, hands-on coding experience in GenAI domains, also, the application should take ownership in the tasks assigned to them.● We will critically evaluate your problem statement understanding, system design, theoretical understanding of LLM techniques/models, hands-on coding experience in GenAI domains, also, the application should take ownership in the tasks assigned to them.● Transformer & Multimodal Mastery: Deep expertise in transformer architectures (GPT, LLaMA, BERT, T5) and multimodal models (e.g., CLIP, Flamingo)● Agentic Protocols & Platforms: Hands-on with MCP, A2A protocols, and agent toolkits such as Agent Builder and AgentSpace● Proficiency with frameworks like PyTorch, TensorFlow, and frameworks like LangChain, Hugging Face, transformers, llamaindex, ollama, LLM360, texgen-webUI, or other model orchestration libraries● RAG Proficiency: Proven track record designing, deploying, and scaling retrieval-augmented generation systems in production● LLM Orchestration: Extensive use of LangChain, AutoGen, llamaindex, or similar for multi-step reasoning workflows● Experience in designing, deploying, and orchestrating multi-agent systems using LLM-based agents for dynamic task execution across various tools and platforms using langgraph, langchain, autogen, or llamaindex.● Familiarity with tool-calling frameworks, LLM-sandboxing, and how LLMs can interact with external systems (e.g., databases, APIs).● MLOps & Cloud: Production deployments on AWS/Azure/GCP using Docker, Kubernetes, Terraform, CI/CD, and monitoring stacks● Advanced Prompting: Mastery of Chain of Thought (CoT), Tree of Thought (ToT), Graph of Thought (GoT), and self-critique strategies● Software Engineering Rigor: Solid understanding of SOLID principles, version control (Git), unit/integration testing, and code review culture● Collaboration & Communication: Excellent at articulating technical solutions to both technical peers and non-technical stakeholdersNice-to-Have● Contributions to open-source agentic frameworks or active involvement in AI standards bodies● Familiarity with real-time streaming data, event-driven architectures, or Large Scale deployed AI agentsWhat We Offer● Competitive senior-level salary and equity package● Leadership in defining and building our flagship AI products● Generous professional development budget (conferences, certifications)● Fully remote, flexible work environment with seasoned AI mentorsJoin Steps AI and lead the charge in building the autonomous LLM engines that will power tomorrow’s enterprise intelligence.