Founding Engineer, AI

Cenna; Hyderabad; Vor Ort; INR 900.000 - 1.300.000; Vollzeit

Zusammenfassung

Cenna in Hyderabad is seeking an AI Engineer to design and implement the intelligent core of an agentic platform. You will build multi-agent systems, orchestrate LangChain/LangGraph workflows, and enable LLM-powered reasoning for enterprise automation.

You will optimize RAG pipelines, fine‑tune SLMS, and craft prompts for reliable agent behavior while collaborating with integration engineers across enterprise systems.

Qualifikationen

• 3–5 years of software engineering experience, with 1–2 years focused on AI/ML or LLM applications.
• Strong programming skills in Python.
• Hands-on experience with agent frameworks: LangChain, LangGraph, CrewAI, AutoGen, Haystack or similar.
• Experience building applications with LLM APIs (OpenAI, Anthropic, Azure OpenAI, open‑source models).
• Understanding of prompt engineering, chain-of-thought reasoning, and tool‑use patterns.
• Familiarity with RAG architectures, vector databases, and embedding models.
• Ability to debug complex AI systems and iterate based on real‑world failures.
• Strong communication skills and ability to work cross‑functionally.

Aufgaben

• Design and build multi-agent systems that orchestrate complex business process automation
• Work with agent frameworks (LangChain, LangGraph, CrewAI, AutoGen, or similar) to build reliable, production-grade agentic workflows
• Implement and optimize LLM-powered reasoning, planning, and tool‑use capabilities
• Build RAG pipelines and knowledge retrieval systems to ground agents in enterprise context
• Fine‑tune and evaluate Small Language Models (SLMs) for domain-specific tasks
• Develop prompt engineering strategies and evaluation frameworks for agent reliability
• Collaborate with integration engineers to connect agents with enterprise systems
• Debug and improve agent behavior based on production feedback and failure analysis

Kenntnisse

Python

LLM APIs

Agent frameworks

RAG

Vector databases

Prompt engineering

Multi-agent systems

Performance optimization

Tools

LangChain

LangGraph

CrewAI

AutoGen

Haystack

OpenAI

Jobbeschreibung

Build our agentic services platform from zero to one. Own backend architecture from initial concept through production deployment to enterprise scale.

About This Role

We're looking for an AI Engineer to build and improve the intelligent core of our agentic platform. You'll work on multi-agent systems, LLM orchestration, and the AI capabilities that power our enterprise automation. This is a hands‑on role where you'll design, implement, and optimize AI systems that execute real business processes — not just chatbots, but agents that get work done.

Responsibilities

• Design and build multi-agent systems that orchestrate complex business process automation
• Work with agent frameworks (LangChain, LangGraph, CrewAI, AutoGen, or similar) to build reliable, production-grade agentic workflows
• Implement and optimize LLM-powered reasoning, planning, and tool‑use capabilities
• Build RAG pipelines and knowledge retrieval systems to ground agents in enterprise context
• Fine‑tune and evaluate Small Language Models (SLMs) for domain-specific tasks
• Develop prompt engineering strategies and evaluation frameworks for agent reliability
• Collaborate with integration engineers to connect agents with enterprise systems
• Debug and improve agent behavior based on production feedback and failure analysis

Requirements

• 3-5 years of experience in software engineering, with at least 1-2 years focused on AI/ML or LLM applications
• Strong programming skills in Python
• Hands‑on experience with agent frameworks: LangChain, LangGraph, CrewAI, AutoGen, Haystack, or similar
• Experience building applications with LLM APIs (OpenAI, Anthropic, Azure OpenAI, open‑source models)
• Understanding of prompt engineering, chain-of-thought reasoning, and tool‑use patterns
• Familiarity with RAG architectures, vector databases, and embedding models
• Ability to debug complex AI systems and iterate based on real‑world failures
• Strong communication skills and ability to work cross‑functionally

Nice to Have

• Experience fine‑tuning LLMs or training custom models (LoRA, PEFT, etc.)
• Familiarity with browser/computer‑use agents and UI automation
• Experience with ML infrastructure: model serving, GPU optimization, inference at scale
• Background in reinforcement learning or decision‑making systems
• Understanding of enterprise IT, ITSM, or business process automation
• Startup experience or comfort working in fast‑paced, ambiguous environments

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.