Job Description

Job Title : AI Engineer

Company : Space O Technologies

Years of Experience: 4+ years

Location: Ahemdabad

Role Type: Full-Time

Salary: Not specified

Eligibility: Candidates with deep expertise in AI agent systems, RAG pipelines, LLM tooling, and production-grade GenAI deployments

Role Overview:

Design, develop, and deploy intelligent AI agent systems and retrieval-augmented generation (RAG) pipelines. Build production-grade GenAI applications using frameworks like LangGraph, CrewAI, and LangChain, integrating agents with internal tools, APIs, and databases. Collaborate with research and product teams to optimize multi-agent workflows and ensure robust monitoring, logging, and observability in production environments.

Key Responsibilities:

• Design and implement AI agent frameworks with memory, tool use, task decomposition, and multi-turn conversation capabilities.
• Build and optimize RAG pipelines using LangChain, LlamaIndex, or custom vector search architectures.
• Integrate agents with internal tools, APIs, and databases to support real-world applications.
• Collaborate with ML researchers and product teams to experiment with novel architectures and orchestrators like LangGraph and CrewAI.
• Monitor, evaluate, and optimize model performance using telemetry, logging, and analytics.
• Deploy production-ready systems with robust CI/CD pipelines, testing, and monitoring.
• Stay current with advances in LLMs, agentic frameworks, and vector search infrastructure.

Skills and Qualifications:

• Programming: Python (advanced), TypeScript/Node.js (nice to have)
• AI Frameworks: LangGraph, CrewAI, LangChain, LlamaIndex, OpenAI, Hugging Face
• Agent Systems: Designing multi-agent workflows, task planning, memory handling, inter-agent communication
• RAG Architecture: Document loaders, chunking strategies, embeddings, hybrid search, contextual reranking
• LLM Tooling: OpenAI GPT-4/4o, Claude, Gemini, local models (Mistral, LLaMA)
• Infrastructure: Vector DBs (Weaviate, Pinecone, Qdrant, Elasticsearch), Postgres, MongoDB
• MLOps: Prompt engineering, model evaluation, A/B testing, observability
• Deployment: REST APIs, FastAPI, Docker, CI/CD pipelines
• Additional: Strong communication skills, independent initiative, familiarity with GenAI safety, audit logging, and access controls