Generative AI Engineer

Core Responsibilities

Multi-Agent System Architecture

• Architect and implement multi-agent workflows using LangChain, LangGraph, AutoGen, CrewAI, Google ADK, CAMEL, Swarm, and OpenAI Agents SDK to orchestrate task decomposition, memory, tool use, and agent coordination.
  

Model Context Protocol (MCP) Integration

• Engineer workflows that use MCP for context-sharing and standardized communication among agents and with external systems (SQL, file systems, tools).
  

Agent Framework Development

• Design abstracted agent frameworks supporting planning, reasoning, retries, orchestration, and observability.
  

Data Processing & Pipelines

• Develop ETL pipelines for ingestion, transformation, storage, and embedding generation using Airflow, Prefect, Spark, Hadoop, and vector databases (FAISS, Pinecone, Weaviate).
  

LLM Fine‑Tuning & RAG Architecture

• Fine‑tune GPT, LLaMA, Claude, Mistral models with efficient methods; build retrieval‑augmented systems using vector DBs and knowledge graphs.
  

Multimodal AI & API Integration

• Integrate text, image, audio, OCR, and structured data (via CLIP, Whisper, TTS/STT); expose capabilities through REST/GraphQL APIs and microservices.
  

Production MLOps & Engineering

• Follow core Python engineering practices—OOP, async, unit testing, packaging. Containerize with Docker and deploy on Kubernetes or serverless infra.
  

Ethics, Security & Performance Optimization

• Integrate bias detection, explainability, privacy safeguards (prompt injection mitigation), and optimize performance and cost.
  

Requirements

Education:

• BSc or MSc in Computer Science, Engineering, Data Science, or equivalent.
  

Technical Skills:

• Python: Advanced proficiency in OOP, async programming, packaging, testing.
  

• LLM Frameworks: Hugging Face Transformers, PyTorch, TensorFlow.
  

• Agent Frameworks: Experience with LangChain, LangGraph, AutoGen, CrewAI, ADK.
  

• Protocols: Deep understanding of MCP, A2A, and agent interoperability.
  

• Data Engineering: Airflow, Prefect, Spark/Hadoop, SQL/NoSQL, vector databases.
  

• Cloud & Containerization: Experience with AWS, GCP, Azure, Docker, Kubernetes.
  

• API & Microservices: FastAPI, Flask, GraphQL, event-driven systems.
  

• RAG Systems: Expertise in FAISS, Pinecone, ChromaDB, Weaviate, and knowledge graphs.
  

• Software Quality & Architecture: Strong foundations in system design, scalability, security, and CI/CD best practices.
  

• Proven track record in full-stack AI agent deployment.
  

• Deep familiarity with prompt engineering, decision chaining, and tool integrations.
  

• Background in reinforcement learning, planning, or control-loop architectures.
  

Soft Skills:

• Excellent communication and collaboration across multidisciplinary teams.
  

• Analytical mindset with strong debugging and iterative development approach.
  

• Agile-oriented: rapid experimentation, evaluation, and adaptation.