Advanced AI & Data Science Specialist – Multi‑Agent Intelligence

Key Responsibilities

AI System & Agentic Workflows

• Design, build, and optimize agentic AI systems using modern agent frameworks (e.g., LangGraph, AutoGen, Haystack Agents, ReAct-style agents).
• Implement multi-agent collaboration patterns, task orchestration, memory architectures, tool integrations, and reasoning-enhancing strategies.
• Develop secure, robust, and scalable toolcalling and function-execution flows for agents operating in dynamic environments.

RAG Architecture & LLM Applications

• Architect and deploy RAG pipelines, including:
• Document ingestion, text splitting, metadata extraction
• Vector database integration (e.g., Postgress)
• Query transformation, retrieval optimization, re-ranking, and grounding
• Evaluate and optimize RAG components for latency, accuracy, hallucination reduction, and domain specificity.
• Integrate RAG workflows with LLMs from OpenAI, Azure OpenAI, Anthropic, or open-source models.

Data Science & Machine Learning

• Build and maintain endtoend ML pipelines including feature engineering, model training, hyperparameter tuning, and deployment.
• Conduct exploratory data analysis (EDA), statistical modeling, and experiment design.
• Implement MLOps practices for versioning, monitoring, and model governance.

Software Engineering & Deployment

• Build production-grade APIs and microservices for AI systems.
• Work with cloud platforms (Azure/AWS/GCP) to deploy scalable and cost-efficient AI infrastructure.
• Establish CI/CD workflows for model deployment, evaluations, and automated testing.

Required Skills & Qualifications

Technical Expertise

• 8+ years of industry experience in AI/ML engineering, data science, or fullstack AI solution architecture.
• Strong proficiency in Python, including libraries such as PyTorch, TensorFlow, LangChain/LangGraph, LlamaIndex, Hugging Face, and Scikit-learn.
• Deep understanding of LLMs, embeddings, vector search, and RAG best practices.
• Experience with agentic AI architectures, tool-calling, and autonomous agent design.
• Hands-on experience with cloud-based AI services (Azure AI, AWS SageMaker, GCP Vertex AI).
• Strong data engineering fundamentals (Spark, SQL, ETL pipelines).
• Experience deploying AI systems in production using containers (Docker), Kubernetes, or serverless architectures.

Soft Skills

• Strong problem-solving and analytical skills.
• Excellent communication and documentation capabilities.
• Ability to collaborate with cross-functional teams (Product, Engineering, Data, DevOps).
• Ownership mindset with strong focus on delivering high-quality solutions.

Preferred (Nice-to-Have) Skills

• Experience with evaluation frameworks (e.g., RAGAS, LangSmith, DeepEval).
• Familiarity with knowledge graph augmentation for enterprise RAG.
• Exposure to multi-modal AI systems (vision, speech, structured data).
• Understanding of data privacy, compliance, and AI safety practices.