Senior Data and Agentic engineer

echnology Solutions is a global IT services and consulting company that helps enterprises reimagine and realign their businesses to stay ahead in the digital age. The organization delivers value through custom software development, flexible delivery models, and tailored solutions aligned with clients’ strategic and commercial goals. Continuous innovation and a strong focus on customer success are central to the company’s culture, measured by quality of deliverables, time to market, ROI, and cost optimization. Ennovision’s portfolio spans Salesforce strategy and implementation, e-commerce and m-commerce platforms, enterprise architecture consulting, cloud services, data science, AI and ML, big data and analytics, QA services, and outsourcing/offshoring.

Senior Agentic AI & Data Engineer
Experience: 6–10 years
Role Type: Senior Engineer / Lead Engineer
Primary Skills: Python, Data Engineering, LLMs, Agentic AI, RAG, Cloud

Role Overview
We are looking for a Senior Agentic AI & Data Engineer who combines strong, production-grade data engineering experience with hands-on expertise in building LLM and Agentic AI solutions.
This is not a pure Data Engineering role and is not a prompt-engineering role. We are looking for an engineer who understands how enterprise data is ingested, transformed, governed and served — and can build intelligent agents and AI-driven workflows on top of that data ecosystem.
The ideal candidate should be comfortable moving between data pipelines, APIs, LLMs, RAG architectures and autonomous/multi-agent workflows, taking solutions from experimentation through to production.

Key Responsibilities
• Design and develop Agentic AI applications that can reason, retrieve information, invoke tools/APIs and execute multi-step workflows.
• Build and orchestrate single-agent and multi-agent systems, including tool calling, state management, memory, routing and human-in-the-loop patterns.
• Develop production-grade LLM and RAG applications using structured and unstructured enterprise data.
• Design efficient retrieval architectures using embeddings, vector databases, metadata filtering, reranking and contextual retrieval.
• Build scalable batch, streaming and real-time data pipelines to supply trusted enterprise data to AI applications.
• Develop data ingestion, transformation, validation, deduplication and enrichment pipelines.
• Integrate agents with enterprise systems, databases, APIs, data warehouses and event-driven platforms.
• Implement evaluation, observability and monitoring for Agentic AI systems, including response quality, hallucination, latency, cost and agent/tool failures.
• Design guardrails and validation mechanisms to ensure agents operate reliably within defined business processes.
• Optimise data and AI workloads for performance, reliability, scalability and cloud cost.
• Work closely with business, product and engineering teams to identify processes where agents can replace or automate manual data and operational workflows.
• Take ownership of solutions from initial POC through engineering, deployment, monitoring and production optimisation.

Essential Technical Skills
• Agentic AI & Generative AI
• Strong hands-on experience with:
• LLM-powered application development
• Agentic workflows and tool/function calling
• RAG architectures
• Prompt and context engineering
• Structured LLM outputs
• Vector search and embeddings
• LLM evaluation and observability
• OpenAI, Claude, Gemini or equivalent enterprise LLM platforms
• Frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel or equivalent

Candidates should understand the engineering challenges involved in moving an Agentic AI solution from a successful demonstration into a reliable production system.
Data Engineering

Strong experience with:
• Python
• Apache Spark / PySpark
• Apache Kafka or equivalent streaming technologies
• Apache Airflow or similar workflow orchestration platforms
• ETL/ELT pipeline development
• Batch and streaming architectures
• Data quality and validation
• Schema evolution and data contracts
• SQL and data modelling
• Large-scale distributed data processing

Data Platforms
Experience with a combination of:
• Data Warehouse Solutions: Snowflake, Databricks, Google BigQuery, Amazon Redshift.
• Database Management Systems: PostgreSQL, MongoDB.
• Search and Indexing Technologies: Elasticsearch, Vector databases / vector search technologies.

Cloud & Engineering
Strong experience with the AWS cloud.