AI / Generative AI Engineer – Python, LLMs, RAG, AI Agents, Azure OpenAI & AWS Bedrock

Job Summary

Synechron is seeking an AI / Generative AI Engineer with 6+ years of experience in designing, developing and deploying AI-powered applications. The role will focus on Generative AI, Large Language Models (LLMs), Agentic AI, Retrieval-Augmented Generation (RAG), cloud-based AI platforms and production-grade software engineering.

The position will work with business stakeholders, solution architects, engineering teams, DevOps and MLOps teams to deliver scalable AI solutions that address business needs, integrate with enterprise applications and operate reliably in production environments.

This is a full-time position based in Pune, Bengaluru, Hyderabad or Mumbai, with a hybrid working model. The role contributes to business objectives by accelerating AI adoption, improving automation, enabling intelligent applications and delivering secure, maintainable and measurable AI capabilities.

Software Requirements

Required

• Python: Strong hands-on experience in Python development for AI applications, data processing, model integration and API development; experience with the project-supported version.
• Generative AI and LLMs: Practical experience developing applications using LLMs and foundation models.
• NLP and Transformers: Working knowledge of Natural Language Processing, Transformers, embeddings and prompt engineering.
• RAG: Experience designing and implementing Retrieval-Augmented Generation pipelines.
• Vector Databases: Experience with one or more of the following:PineconeChromaDBFAISSWeaviateEquivalent vector database technologies
• LangChain and LangGraph: Hands-on experience building LLM applications, orchestration workflows or AI agents using current project-supported versions.
• Agentic AI Frameworks: Experience developing intelligent AI agents and agentic workflows.
• Model Context Protocol (MCP): Working knowledge or practical experience applying MCP concepts in AI applications.
• OpenAI / Azure OpenAI: Experience integrating and using OpenAI or Azure OpenAI services.
• AWS Bedrock: Experience using AWS Bedrock or equivalent managed foundation-model services.
• Hugging Face Ecosystem: Familiarity with relevant models, libraries and tools used for Generative AI development.
• Cloud Platforms: Hands-on experience with Azure and/or AWS.
• REST APIs and FastAPI: Experience designing or integrating REST APIs and developing AI services using FastAPI.
• Docker and Kubernetes: Experience containerizing and deploying AI applications and services.
• CI/CD Pipelines: Experience supporting automated build, test and deployment pipelines.
• Git and GitHub/GitLab: Experience with source control, branching, code review and collaborative development.
• SQL and NoSQL Databases: Experience working with structured and unstructured data stores.
• Data Pipelines: Experience with data ingestion, preparation and processing pipelines.
• MLOps: Experience with model deployment, monitoring and machine learning lifecycle management.
• AI Guardrails and Responsible AI: Understanding of guardrails, governance, safety, monitoring and responsible use of AI.

Preferred

• Experience delivering enterprise-scale Generative AI solutions.
• Experience with Copilot solutions, AI agents and multi-agent systems.
• Exposure to the BFSI domain.
• Experience with React, Node.js or full-stack development.
• Understanding of security, compliance and governance requirements for AI applications.
• Experience with knowledge graphs and semantic search solutions.
• Experience with multimodal AI applications.
• Experience with fine-tuning strategies and LLM evaluation frameworks.

Overall Responsibilities

• Design, develop and deploy Generative AI solutions using LLMs and foundation models.
• Build end-to-end AI applications covering data ingestion, prompt engineering, RAG pipelines, model orchestration and API integration.
• Develop intelligent AI agents and agentic workflows using LangChain, LangGraph, MCP and other suitable orchestration frameworks.
• Implement AI capabilities using Azure OpenAI, AWS Bedrock, OpenAI APIs and related AI services.
• Design, configure and manage vector databases and semantic search solutions.
• Create scalable APIs and microservices that integrate AI capabilities into enterprise applications.
• Optimize LLM performance through prompt engineering, fine-tuning strategies, retrieval optimization and evaluation frameworks.
• Establish appropriate methods for measuring response quality, relevance, accuracy, latency, reliability and cost.
• Implement AI guardrails, responsible AI practices, monitoring and governance mechanisms.
• Collaborate with DevOps and MLOps teams on deployment, monitoring, model lifecycle management and production support.
• Apply software engineering practices including version control, code reviews, automated testing, documentation and maintainable architecture.
• Work with business stakeholders and solution architects to understand requirements and translate them into practical AI solutions.
• Assess technical feasibility, integration dependencies, data requirements, risks and operational considerations.
• Stay current with developments in Generative AI, Agentic AI, multimodal AI and LLM ecosystems.
• Support sustainable AI engineering by considering model efficiency, resource utilization, infrastructure cost, reuse and long-term maintainability.
• Deliver production-grade AI solutions that meet agreed functional, security, scalability, reliability and support expectations.

Technical Skills (By Category)

Programming Languages

Essential

• Strong Python development skills.
• Ability to write modular, testable, maintainable and production-ready code.
• Ability to develop AI application logic, data-processing components, API services and integration utilities.

Preferred

• JavaScript or TypeScript experience for AI application integration or full-stack development.
• Node.js experience for backend services.
• React experience for developing or integrating AI-enabled user interfaces.

Databases and Data Management

Essential

• Experience with SQL and NoSQL databases.
• Experience designing and supporting data ingestion and processing pipelines.
• Understanding of structured, unstructured and semi-structured data.
• Experience with vector databases, embeddings, indexing and similarity search.
• Understanding of knowledge graph and semantic search concepts.
• Ability to assess data quality, data access, data lineage and data relevance for AI applications.

Preferred

• Experience with large-scale data processing architectures.
• Experience integrating knowledge graphs with RAG or semantic search solutions.
• Experience optimizing vector search performance and retrieval quality.
• Experience with data governance and metadata management.

Cloud Technologies

Essential

• Hands-on experience with Azure and/or AWS cloud platforms.
• Practical experience using Azure OpenAI, AWS Bedrock or related cloud AI services.
• Understanding of cloud-based deployment, scalability, availability, monitoring and access control.
• Ability to integrate cloud AI services with APIs, databases and enterprise applications.

Preferred

• Experience designing enterprise-scale AI platforms on cloud infrastructure.
• Experience with cloud-based model monitoring, managed AI services and infrastructure automation.
• Experience optimizing cloud resource usage and AI application costs.

Frameworks and Libraries

Essential

• LangChain and LangGraph for LLM application development and orchestration.
• Agentic AI frameworks for AI-agent and agentic workflow development.
• OpenAI and/or Azure OpenAI integration.
• AWS Bedrock integration.
• Hugging Face ecosystem.
• FastAPI for AI service and REST API development.
• RAG architectures, prompt engineering, Transformers and embeddings.
• Experience with LLM-based applications and foundation models.

Preferred

• Frameworks for multi-agent systems and Copilot solutions.
• Libraries and tools for LLM evaluation, model fine-tuning and response-quality measurement.
• Frameworks for multimodal AI applications.
• Libraries for model serving, observability and AI application monitoring.

Development Tools and Methodologies

Essential

• Git and GitHub/GitLab for source control and collaborative development.
• Docker for containerizing AI applications and services.
• Kubernetes for deploying and managing containerized workloads.
• CI/CD pipelines for automated build, test and deployment activities.
• MLOps practices covering model deployment, monitoring, versioning and lifecycle management.
• API-first and microservices-based development.
• Code reviews, technical documentation, automated testing and defect resolution.
• Agile development and collaborative delivery practices.

Preferred

• Experience with infrastructure-as-code and automated environment provisioning.
• Experience implementing model-performance monitoring, data-drift monitoring, latency tracking and usage monitoring.
• Experience with release governance and production support for AI applications.

Security Protocols

Essential

• Understanding of secure AI application design, API security, authentication and authorization.
• Awareness of data privacy, secure data handling and access-control requirements.
• Ability to implement or support AI guardrails for prompt safety, data protection and response control.
• Understanding of responsible AI practices, governance, monitoring and human oversight.
• Ability to identify risks related to prompt injection, data leakage, unauthorized access and unsafe model outputs.

Preferred

• Experience implementing AI governance and model-risk controls.
• Familiarity with security and compliance requirements for AI applications in regulated or data-sensitive environments.
• Experience supporting auditability, explainability and traceability of AI outputs and model activity.

Experience Requirements

• At least 6 years of experience in software development, artificial intelligence, machine learning, data engineering or a related technical field.
• Hands-on experience designing, developing and deploying AI-powered applications.
• Strong practical experience with Generative AI, LLMs, NLP, Transformers, embeddings and prompt engineering.
• Experience implementing RAG architecture and vector database solutions.
• Experience developing AI agents and agentic workflows using LangChain, LangGraph, MCP or similar frameworks.
• Experience with Azure OpenAI, AWS Bedrock, OpenAI APIs or related cloud AI services.
• Experience developing REST APIs and microservices using FastAPI or similar technologies.
• Experience with Docker, Kubernetes, CI/CD pipelines, Git and GitHub/GitLab.
• Experience with SQL and NoSQL databases, data ingestion and data processing pipelines.
• Experience with model deployment, monitoring and MLOps practices.
• Experience delivering enterprise-scale Generative AI solutions.
• Exposure to the BFSI domain.
• Preferred: Experience with Copilot solutions, multi-agent systems, multimodal AI or full-stack development.
• Preferred: Experience with AI governance, responsible AI, model monitoring, security and compliance.
• Candidates may qualify through equivalent practical experience in software engineering, machine learning engineering, data engineering, AI platform engineering or Generative AI application development that demonstrates the required capabilities.

Day-to-Day Activities

• Develop and enhance Generative AI applications, RAG pipelines, AI agents, prompts, APIs, microservices and supporting data-ingestion components.
• Collaborate with business stakeholders, solution architects, engineers, DevOps and MLOps teams to refine requirements, assess designs and coordinate delivery.
• Test and evaluate model responses, retrieval quality, performance, security, guardrails, reliability and operational readiness.
• Make implementation recommendations within the agreed architecture and governance framework while documenting decisions, risks, dependencies and production-support requirements.

Qualifications

• A bachelor’s or master’s degree in Computer Science, Artificial Intelligence, Data Science or a related field is preferred; equivalent relevant experience may be considered.
• Certifications in Azure AI, AWS Machine Learning or equivalent cloud technologies are preferred.
• Practical training or demonstrated experience in Generative AI, LLMs, RAG, prompt engineering, AI agents, cloud AI services and MLOps is required.
• Training in secure software development, responsible AI, data privacy, AI governance and model monitoring is preferred.
• Commitment to continuous professional development in Generative AI, Agentic AI, multimodal AI, cloud platforms, LLM ecosystems and emerging AI engineering practices is expected.

Professional Competencies

• Applies critical thinking to select suitable AI approaches, evaluate model limitations, analyze data and resolve application or production issues.
• Works effectively with business stakeholders, solution architects, engineering teams, DevOps teams and MLOps teams to deliver integrated solutions.
• Communicates technical designs, model behavior, risks, trade-offs, delivery progress and recommendations clearly to technical and non-technical audiences.
• Adapts to rapidly changing AI technologies, frameworks, cloud services, governance expectations and business requirements.
• Identifies practical opportunities to apply Generative AI, Agentic AI, automation, semantic search and reusable components to create measurable value.
• Manages priorities, dependencies, delivery commitments and technical risks while maintaining appropriate standards for quality, security, scalability and maintainability.

S YNECHRON’S DIVERSITY & INCLUSION STATEMENT

Diversity & Inclusion are fundamental to our culture, and Synechron is proud to be an equal opportunity workplace and is an affirmative action employer. Our Diversity, Equity, and Inclusion (DEI) initiative ‘Same Difference’ is committed to fostering an inclusive culture - promoting equality, diversity and an environment that is respectful to all. We strongly believe that a diverse workforce helps build stronger, successful businesses as a global company. We encourage applicants from across diverse backgrounds, race, ethnicities, religion, age, marital status, gender, sexual orientations, or disabilities to apply. We empower our global workforce by offering flexible workplace arrangements, mentoring, internal mobility, learning and development programs, and more.

All employment decisions at Synechron are based on business needs, job requirements and individual qualifications, without regard to the applicant’s gender, gender identity, sexual orientation, race, ethnicity, disabled or veteran status, or any other characteristic protected by law.

Candidate Application Notice