Enterprise AI Developer with Python

Trigent Software Private Limited

Job Location:

Bengaluru - India

Monthly Salary: Not Disclosed

Posted on: 2 hours ago

Vacancies: 1 Vacancy

Job Summary

Virtusa is a global product and platform engineering services company that makes experiences better with technology. We help organizations grow faster more profitably and more sustainably by reimagining enterprises through domain-driven solutions. We combine strategy design and engineering backed by unmatched expertise at the intersection of industry business and technology to generate real-world business impact for clients. Headquartered in Massachusetts with global delivery centers Virtusa provides a broad range of services solutions and assets including strategy and design AI advisory and services digital engineering data and analytics digital assurance cloud and security cx transformation and managed services across industries such as financial services healthcare communications media entertainment travel manufacturing and technology.

Role :

As the Senior AI Developer you will be the core technical architect and engineer responsible for developing optimizing and scaling our enterprise Generative AI platform across various complex systems (both SAP S/4HANA and non-SAP solutions). Operating under a functional division of AI enablement and managed operations your role moves beyond simple wrapper applications. You will build deep enterprise-grade systems of intelligence designing autonomous orchestration workflows multi-agent frameworks and advanced Retrieval-Augmented Generation (RAG) pipelines to replace traditional rule-based IT and application management workflows.

Mandatory Skills

Artificial IntelligencePythonChatbotAWSModel Context Protocol (MCP)Agentic Ai

Skill to Evaluate

Artificial IntelligencePythonChatbotAWSModel Context Protocol (MCP)Agentic Ai

Job Description

Core Engineering Background: 5 years of experience in enterprise software development backend engineering or systems integration with a heavy emphasis on Python or cloud-native microservices.
Generative AI Core Competency: Deep practical experience building applications with Large Language Models (LLMs) designing Retrieval-Augmented Generation (RAG) pipelines and working with vector databases (e.g. pgvector Pinecone or custom S3-backed vector files).
Integration Expertise: Demonstrated mastery in API development (REST gRPC) and connecting conversational layers to complex backend transaction systems (specifically SAP via web services and enterprise ticketing tools like JIRA/BMC Helix).
Protocol & Systems Familiarity: Exposure to modern AI agent communication frameworks multi-agent swarms or open standards like the Model Context Protocol (MCP).
Security Awareness: Solid understanding of the OWASP Top 10 for LLMs and standard data-masking/encryption approaches.

Roles & Responsibilities

1. Hands-On Development & Core Architecture (Catalyst Domain)

Production-Grade AI Engineering: Design build and deploy end-to-end Generative AI use cases from initial proof-of-concept (POC) to robust production environments focusing on Level 1 (L1) support automation and Level 0 (L0) self-healing infrastructure.
Performance Optimization: Implement engineering strategies directly targeted at minimizing Mean Time to Resolution (MTTR) maximizing autonomous ticket deflection and driving project-level operational efficiencies.
Proactive Prototyping: Bring innovative technical solutions and technical design patterns to the table identifying high-volume repetitive IT tasks ripe for agentic automation.

2. Model Optimization Refinement & Analytics (Vector Domain)

LLM Fine-Tuning & Prompt Engineering: Oversee prompt optimization semantic parsing and model fine-tuning utilizing our local Large Language Model (LLM) orchestration layer.
Advanced RAG Engineering: Develop and tune context-aware information discovery loops by engineering vector embeddings implementing search semantic matching and maintaining high-performance vector indexes stored in an Amazon S3 backend.
Operational Telemetry: Build and embed technical logging mechanisms to monitor real-time AI performance track model token costs measure system accuracy and flag hallucinations or behavioral drift.

3. Feature Engineering & Enterprise Ecosystem Integration (Product Domain)

Modular Feature Expansion: Code and package modular reusable AI components and capabilities to allow seamless deployment across a highly diversified portfolio of enterprise projects.
Cross-Platform Integration: Build and maintain the technical pipelines connecting the conversational AI frontier with backend core systems using our specific technology stack:
- Ticketing & ITSM Hooking: Direct API integration and automated triage logic feeding into JIRA and BMC Helix.
- Knowledge Repositories: Data ingestion pipelines linking to Confluence and SharePoint to feed contextual enterprise documentation into the model.
- SAP Backend Hooking: Interfacing with SAP environments by routing secure schema-validated requests via Informatica API pipelines directly to S/4HANA.
- Agent Protocols: Implementing emerging standardization frameworks like the Model Context Protocol (MCP) and multi-agent state isolation layers.

Security-by-Design Alignment: Partner closely with InfoSec teams to build rigorous input/output filtering frameworks Named Entity Recognition (NER) for PII masking and defensive measures against prompt injection or excessive agency.

4. Technical Delivery & Operational Stewardship (Navigator Domain)

Execution Excellence: Track individual and team delivery sprints resolving technical impediments and code blockers to ensure programmatic delivery goals are met.
Meticulous Technical Documentation: Document and update all active codebase modifications system components and framework architectures on the enterprise project tracking platform (SPARK).
Technical Communication: Bridge communications between development squads and business units providing clarity around API contracts data dependencies and system limitations.

Role :

Mandatory Skills

Artificial IntelligencePythonChatbotAWSModel Context Protocol (MCP)Agentic Ai

Skill to Evaluate

Artificial IntelligencePythonChatbotAWSModel Context Protocol (MCP)Agentic Ai

Job Description

Core Engineering Background: 5 years of experience in enterprise software development backend engineering or systems integration with a heavy emphasis on Python or cloud-native microservices.
Generative AI Core Competency: Deep practical experience building applications with Large Language Models (LLMs) designing Retrieval-Augmented Generation (RAG) pipelines and working with vector databases (e.g. pgvector Pinecone or custom S3-backed vector files).
Integration Expertise: Demonstrated mastery in API development (REST gRPC) and connecting conversational layers to complex backend transaction systems (specifically SAP via web services and enterprise ticketing tools like JIRA/BMC Helix).
Protocol & Systems Familiarity: Exposure to modern AI agent communication frameworks multi-agent swarms or open standards like the Model Context Protocol (MCP).
Security Awareness: Solid understanding of the OWASP Top 10 for LLMs and standard data-masking/encryption approaches.

Roles & Responsibilities

1. Hands-On Development & Core Architecture (Catalyst Domain)

Production-Grade AI Engineering: Design build and deploy end-to-end Generative AI use cases from initial proof-of-concept (POC) to robust production environments focusing on Level 1 (L1) support automation and Level 0 (L0) self-healing infrastructure.
Performance Optimization: Implement engineering strategies directly targeted at minimizing Mean Time to Resolution (MTTR) maximizing autonomous ticket deflection and driving project-level operational efficiencies.
Proactive Prototyping: Bring innovative technical solutions and technical design patterns to the table identifying high-volume repetitive IT tasks ripe for agentic automation.

2. Model Optimization Refinement & Analytics (Vector Domain)

LLM Fine-Tuning & Prompt Engineering: Oversee prompt optimization semantic parsing and model fine-tuning utilizing our local Large Language Model (LLM) orchestration layer.
Advanced RAG Engineering: Develop and tune context-aware information discovery loops by engineering vector embeddings implementing search semantic matching and maintaining high-performance vector indexes stored in an Amazon S3 backend.
Operational Telemetry: Build and embed technical logging mechanisms to monitor real-time AI performance track model token costs measure system accuracy and flag hallucinations or behavioral drift.

3. Feature Engineering & Enterprise Ecosystem Integration (Product Domain)

Modular Feature Expansion: Code and package modular reusable AI components and capabilities to allow seamless deployment across a highly diversified portfolio of enterprise projects.
Cross-Platform Integration: Build and maintain the technical pipelines connecting the conversational AI frontier with backend core systems using our specific technology stack:
- Ticketing & ITSM Hooking: Direct API integration and automated triage logic feeding into JIRA and BMC Helix.
- Knowledge Repositories: Data ingestion pipelines linking to Confluence and SharePoint to feed contextual enterprise documentation into the model.
- SAP Backend Hooking: Interfacing with SAP environments by routing secure schema-validated requests via Informatica API pipelines directly to S/4HANA.
- Agent Protocols: Implementing emerging standardization frameworks like the Model Context Protocol (MCP) and multi-agent state isolation layers.

Security-by-Design Alignment: Partner closely with InfoSec teams to build rigorous input/output filtering frameworks Named Entity Recognition (NER) for PII masking and defensive measures against prompt injection or excessive agency.

4. Technical Delivery & Operational Stewardship (Navigator Domain)

Execution Excellence: Track individual and team delivery sprints resolving technical impediments and code blockers to ensure programmatic delivery goals are met.
Meticulous Technical Documentation: Document and update all active codebase modifications system components and framework architectures on the enterprise project tracking platform (SPARK).
Technical Communication: Bridge communications between development squads and business units providing clarity around API contracts data dependencies and system limitations.