AI Engineer

Recode Solutions; Chennai; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Recode Solutions in Chennai is seeking an AI/Data Developer with strong Python, Azure Databricks, Delta Lake, and AI/LLM expertise. You will design Databricks jobs, reusable scripts, and cloud-native microservices, and lead Copilot agentic workflows to enable enterprise AI use cases.

You will build LLm-driven AI scenarios, integrate with Databricks and data lakes, and own end-to-end deliverables with minimal supervision.

Qualifications

• 8–10 years of Python, data engineering, or backend development.
• Experience in enterprise cloud environments.
• Exposure to streaming platforms (Kafka, Event Hubs) preferred.

Responsibilities

• Design, develop, and manage Azure Databricks jobs, workflows, and notebooks.
• Build reusable Python/PySpark scripts for data ingestion and analytics.
• Implement Delta Lake-based lakehouse architectures with ACID and versioning.
• Optimize workloads for performance, scalability, and cost.
• Develop Python-based microservices exposing data and AI capabilities via APIs.

Skills

Python

PySpark

LLMs

Copilot workflows

Tools

Databricks

REST APIs

FastAPI

Docker

Terraform

Job description

Job Summary

We are looking for aAIDeveloperwith strong expertise inPython,Azure Databricks (ADB),Delta Lake, andAI/LLM technologiesto design and buildDatabricks jobs, reusable scripts, and cloud-native microservices. The role requires hands-on experience withCopilot agentic mode (or equivalent), buildingLLM-drivenAIuse cases, and the ability towork independently by taking full ownership of deliverables without the need for micromanagement.

Roles and Responsibilities

• Design, develop, and manageAzure Databricks jobs, workflows, and notebooks.
  
• Build reusablePython/PySpark scriptsfor data ingestion, transformation, and analytics.
  
• ImplementDelta Lake–based lakehouse architectureswith ACID transactions and versioning.
  
• Optimize Databricks workloads forperformance, scalability, and cost efficiency.
  
• Implement batch and streaming pipelines using Databricks.
  

Microservices & Application Development

• DevelopPython-based microservicesto expose data andAIcapabilities via APIs.
  
• Build and integrate RESTful services for data access,AIinference, and orchestration.
  
• Ensure secure, scalable, and resilient service design using cloud-native patterns.
  
• Drive development tasks independently, from design through deployment, with minimal supervision.
  

AI, LLMs & Copilot Agentic Mode

• Design and buildLLM-poweredAIuse casessuch as copilots, intelligent assistants, and automation agents.
  
• ImplementCopilot agentic modeworkflows, including tool calling, task planning, and multi-step reasoning.
  
• Developprompt engineering strategies, system prompts, and guardrails for enterprise use.
  
• Integrate LLMs with Databricks, data lakes, and microservices for real-time and batch inference.
  
• BuildRAG (Retrieval-Augmented Generation)pipelines using enterprise data.
  
• Evaluate, fine-tune, and monitor LLM performance, accuracy, and cost.
  

Architecture, Governance & Best Practices

• Contribute tosolution architectureand technical design decisions.
  
• Ensure data security, governance, and compliance in data andAIsolutions.
  
• Implement logging, monitoring, and observability for Databricks jobs andAIservices.
  
• Perform code reviews and enforce engineering best practices.
  
• Mentor peer developers and provide technical guidance when needed.
  
• Collaborate effectively with data scientists, architects, DevOps teams, and business stakeholders.
  
• Clearly communicate technical concepts, progress, and risks throughexcellent verbal and written communication skills.
  
• Take full ownership of assigned workstreams and drive them to completion without requiring micromanagement.
  

Required Technologies & Skills

Programming & Frameworks

• Python (advanced)
  
• PySpark / Spark SQL
  
• REST APIs and microservices frameworks (FastAPI, Flask, etc.)
  
• Azure cloud services and security fundamentals
  
• Hands-on experience withLLMs(Azure OpenAI, OpenAI, or similar)
  
• Experience buildingCopilot solutions and agentic workflows
  
• Prompt engineering and orchestration frameworks (LangChain, Semantic Kernel, etc.)
  
• Experience withRAG architectures, vector databases, and embeddings
  
• Understanding ofAIsafety, guardrails, and responsibleAIpractices
  
• Containerization (Docker preferred)
  
• Infrastructure-as-code concepts (Terraform/Bicep – preferred)
  

Preferred Qualifications

• 8 to 10 years of experience inPython, data engineering, or backend development
  
• Experience in enterprise-scale cloud environments
  
• Exposure to streaming platforms (Kafka, Event Hubs – preferred)
  

Soft Skills

• Excellent verbal and written communication skills
  
• Strong sense of ownership and accountability
  
• Ability to work independently and proactively drive outcomes
  
• Strong problem-solving and analytical skills
  
• Collaborative mindset with leadership capabilities