Generative AI Engineer (Python + RAG + Agentic AI)

We are looking for an experienced Generative AI Engineer who can blend strong Python backend engineering with modern AI frameworks to build scalable, production-grade AI systems. The ideal candidate has hands-on expertise with LangChain, LangGraph, FastAPI, RAG pipelines, vector databases, and agentic workflows, and can translate complex business problems into reliable AI-driven solutions.

Responsibilities

Generative AI & LLM Engineering

• Build and optimize RAG pipelines using vector DBs like Pinecone, Weaviate, Supabase, PGVector, etc.

• Develop AI workflows using LangChain, LangGraph, and modern model orchestration tools.

• Implement prompt engineering, prompt templates, response validation, and LLM optimisation.

• Work with embeddings, similarity search, and text-to-vector processing for personalized retrieval.

• Build agentic AI workflows capable of multi-step reasoning, tool usage, and autonomous task execution.

• Handle multimodal workloads involving text, images, or video for processing or generation.

• Integrate observability tools for tracking latency, cost, accuracy, and model behavior.

Backend Engineering (Python)

• Build scalable backend services using FastAPI (preferred), Django, or Flask.

• Design RESTful APIs and backend pipelines for AI workloads, streaming, and multimodal data.

• Implement asynchronous programming and background job execution (Celery, cron, or equivalents).

• Work with relational DBs (PostgreSQL, MySQL) and integrate vector DBs for AI workflows.

• Consume 3rd-party SDKs/APIs, ensuring secure and seamless system integrations.

• Deploy services using Docker, containerized pipelines, and production-grade best practices.

• Implement secure coding practices, RBAC, API security, and scalable architectures.

Required Skills

• Strong proficiency in Python and backend frameworks (FastAPI preferred).

• Deep experience with LangChain, LangGraph, RAG pipelines, vector databases, embeddings.

• Hands-on knowledge of LLMs, prompt engineering, multimodal models, and AI agents.

• Experience deploying AI services with Docker, job schedulers, and scalable backend design.

• Strong understanding of relational DBs + vector DBs.

• Experience with asynchronous programming and writing robust unit/integration tests (Pytest).

• Ability to debug, optimize, and productionize AI applications.

Preferred Skills

• Experience with cloud platforms: AWS, GCP, Azure.

• Basic understanding of frontend technologies (HTML/CSS/JS) for collaboration.

• Familiarity with FastMCP or other model-context-protocol integrations.

• Experience with model monitoring, observability, and performance dashboards.

• Awareness of current trends in generative AI, agentic systems, and multimodal architectures.

Who Will Succeed in This Role?

Someone who:

• Can think end-to-end — from data ingestion to retrieval to orchestration to deployment.

• Enjoys solving complex AI problems with clean, scalable backend design.

• Is hands-on with modern AI tooling, not just theoretical knowledge.

• Thrives in a fast-paced environment where innovation and ownership matter.