AI Engineer – Python, LLM/GenAI, RAG, AWS & AI Agents
Synechron · IT Services & Consulting
- Pune - Hinjewadi (Ascendas)
- On-site
- Posted today
- Apply by 29 Nov
- Data & AI
About the job
Job Summary
Synechron is seeking an AI Engineer to build and implement AI agents and AI architecture within CI/CD workflows on AWS. The role will focus on developing production-ready generative AI solutions, retrieval-augmented generation (RAG) pipelines, agentic workflows, model integrations, and AI-enabled automation.
The AI Engineer will contribute to the design, development, deployment, and continuous improvement of AI solutions using Python, large language models (LLMs), AWS services, vector databases, and secure engineering practices. The role will also support code generation, code fixing, security automation, and remediation systems where applicable.
The position contributes to business objectives by accelerating software delivery, improving engineering productivity, enabling secure AI adoption, automating technical processes, and delivering scalable AI capabilities through reliable cloud-based architectures.
Software Requirements
Required Software Skills
Python: Strong professional experience in Python and AI development, including application design, API development, automation, testing, and production deployment.
LLMs and Generative AI: Minimum 3 years of experience working with LLMs and GenAI, including OpenAI, Bedrock, or similar technologies.
RAG pipeline engineering: Hands-on experience designing and implementing RAG pipelines using SageMaker, Lambda, vector databases, embeddings, document processing, retrieval, and response generation.
MCP server development: Experience developing MCP servers and integrating tools, services, APIs, and data sources with AI applications.
Agentic workflows: Experience building agentic workflows or autonomous AI agents, including task planning, tool use, orchestration, memory, workflow control, and response validation.
Code generation and code fixing using LLMs: Exposure to using LLMs for code generation, code review, code transformation, defect identification, and code remediation.
Vector databases: Experience with vector databases, embedding generation, similarity search, metadata filtering, indexing, and retrieval optimization.
AWS services: Good knowledge of AWS services, including Lambda, ECS/EKS, S3, API Gateway, and SageMaker.
Application security: Understanding of application security principles, common vulnerabilities, secure coding practices, identity and access controls, and protection of AI applications and data.
CI/CD integration: Experience implementing or integrating AI agents and AI architecture within CI/CD workflows on AWS.
Preferred Software Skills
Exposure to CI/CD tools such as GitHub, Jenkins, Harness, or equivalent tools.
Experience with security tools such as Snyk, SonarQube, or equivalent tools.
Knowledge of containerization and orchestration using Docker and Kubernetes.
Prior work in security automation or remediation systems.
Experience with automated testing, code quality checks, vulnerability scanning, and deployment gates.
Experience integrating AI solutions with enterprise APIs, repositories, issue management platforms, and security tools.
Overall Responsibilities
Design, develop, and implement AI agents and AI architecture within CI/CD workflows on AWS.
Build and maintain production-ready generative AI applications using LLMs, including OpenAI, Bedrock, or similar technologies.
Develop RAG pipelines using SageMaker, Lambda, vector databases, embeddings, document ingestion, retrieval, and response-generation components.
Develop MCP servers and integrate tools, APIs, services, data sources, and enterprise systems with AI applications.
Build agentic workflows and autonomous AI agents that can plan tasks, use approved tools, manage context, and produce validated outcomes.
Apply Python engineering practices to create maintainable, testable, observable, and scalable AI solutions.
Support code generation and code fixing using LLMs, including automated code recommendations, remediation workflows, and developer productivity capabilities.
Integrate AI solutions with CI/CD tools, source control, security tools, testing frameworks, and deployment workflows.
Use AWS services, including Lambda, ECS/EKS, S3, API Gateway, and SageMaker, to deploy and operate AI applications.
Apply application security principles to AI architecture, data handling, API access, model interactions, prompts, tools, and generated code.
Evaluate AI solution performance using measurable criteria such as accuracy, relevance, latency, reliability, cost, security, and operational stability.
Collaborate with engineering, DevOps, security, architecture, and business stakeholders to define requirements and deliver AI capabilities.
Contribute to sustainable engineering practices by optimizing model usage, compute consumption, storage, retrieval processes, and cloud resource utilization.
Performance Outcomes and Expectations
AI agents and AI architecture are implemented within defined CI/CD workflows on AWS.
RAG pipelines provide relevant, reliable, secure, and traceable responses based on approved data sources.
AI agents use tools and services according to defined permissions, validation controls, and operational policies.
AI solutions meet agreed performance, security, scalability, cost, and maintainability criteria.
Code generation and code-fixing capabilities improve development productivity while maintaining appropriate review and quality controls.
Vulnerabilities and security risks are identified, documented, prioritized, and addressed through appropriate automation or remediation processes.
AI applications are supported by appropriate testing, monitoring, documentation, and operational procedures.
Technical Skills (By Category)
Programming Languages
Essential
Strong experience with Python for AI development, automation, API integration, data processing, and cloud-based application development.
Ability to write maintainable, testable, modular, and secure Python code.
Experience developing services, scripts, integrations, and automation for LLM and RAG applications.
Preferred
Experience with JavaScript or TypeScript for AI interfaces, service integrations, or tool development.
Experience with shell scripting for automation and CI/CD activities.
Experience working with multiple programming languages in enterprise software environments.
Databases and Data Management
Essential
Experience with vector databases and vector search.
Understanding of embeddings, chunking, indexing, similarity search, metadata filtering, and retrieval optimization.
Experience designing RAG data flows, including document ingestion, preprocessing, storage, retrieval, and response grounding.
Understanding of data security, access controls, retention, and protection of sensitive information used by AI applications.
Preferred
Experience with relational and NoSQL databases.
Experience with managed vector database services and hybrid search.
Knowledge of data quality, data lineage, document versioning, and source validation.
Experience implementing data ingestion and synchronization pipelines.
Cloud Technologies
Essential
Good knowledge of AWS services, including:LambdaECS/EKSS3API GatewaySageMaker
Experience deploying AI applications and services in AWS environments.
Understanding of AWS identity and access management, networking, logging, monitoring, scalability, and cost considerations.
Experience implementing AI agents and AI architecture within AWS-based CI/CD workflows.
Preferred
Experience with additional AWS services for observability, messaging, secrets management, databases, and workflow orchestration.
Experience with serverless and event-driven architectures.
Experience implementing multi-environment deployment strategies.
Experience optimizing cloud resource usage, model inference costs, storage, and compute consumption.
Frameworks and Libraries
Essential
Experience with LLM and GenAI technologies, including OpenAI, Bedrock, or similar platforms.
Experience developing RAG pipelines using SageMaker and Lambda.
Experience with agentic workflows or autonomous AI agents.
Experience developing MCP servers and tool integrations.
Experience with Python libraries and frameworks for AI, data processing, APIs, testing, and automation.
Understanding of prompt design, context management, response validation, and model evaluation.
Preferred
Experience with AI agent orchestration frameworks.
Experience with model evaluation, tracing, observability, and prompt/version management.
Experience with automated code generation, code fixing, code analysis, and software remediation using LLMs.
Experience integrating AI applications with enterprise systems, APIs, repositories, security platforms, and workflow tools.
Development Tools and Methodologies
Essential
Experience integrating AI agents and AI architecture into CI/CD workflows.
Understanding of source control, branching, pull requests, code reviews, automated testing, and deployment practices.
Experience with Python-based software development lifecycle practices.
Understanding of application architecture, API design, distributed systems, and cloud-native development.
Ability to document AI architecture, data flows, agent behavior, tool permissions, dependencies, and operational procedures.
Experience applying quality controls to AI-generated code and AI-enabled development processes.
Preferred
Exposure to CI/CD tools such as GitHub, Jenkins, Harness, or equivalent tools.
Experience with security tools such as Snyk, SonarQube, or equivalent tools.
Knowledge of Docker and Kubernetes.
Experience with security automation or remediation systems.
Experience with automated vulnerability scanning, software composition analysis, static analysis, and security gates.
Experience with DevSecOps, infrastructure automation, and release governance.
Security Protocols
Essential
Understanding of application security principles and common application vulnerabilities.
Knowledge of secure coding, input validation, output validation, dependency management, and secrets protection.
Understanding of authentication, authorization, identity and access management, and least-privilege controls.
Ability to secure LLM applications, RAG pipelines, MCP servers, APIs, prompts, tools, and generated code.
Awareness of risks such as prompt injection, data leakage, insecure tool execution, excessive permissions, malicious content, and untrusted model output.
Experience applying security reviews, vulnerability assessment, and remediation practices to AI and software solutions.
Preferred
Experience using Snyk, SonarQube, or equivalent security and code quality tools.
Prior work in security automation or remediation systems.
Experience integrating security checks into CI/CD pipelines.
Knowledge of AI security testing, model risk controls, data masking, and audit logging.
Experience Requirements
Minimum 8+ years of overall professional experience in software engineering, cloud engineering, AI engineering, data engineering, or related technology roles.
Minimum 3+ years of AI experience , including hands-on work with LLMs, GenAI, Python, RAG pipelines, AI agents, or related AI application development.
Demonstrated experience building and implementing AI agents and AI architecture within CI/CD workflows on AWS.
Hands-on experience with LLMs and GenAI, including OpenAI, Bedrock, or similar technologies.
Experience with RAG pipeline engineering using SageMaker, Lambda, vector databases, embeddings, and retrieval systems.
Experience with MCP server development, tool integrations, agentic workflows, or autonomous AI agents.
Experience with AWS services including Lambda, ECS/EKS, S3, and API Gateway.
Experience applying application security principles to software, cloud, AI, API, and data solutions.
Preferred experience includes CI/CD tools, security tools, Docker, Kubernetes, security automation, and remediation systems.
Candidates may qualify through equivalent professional experience, demonstrable production AI implementations, substantial open-source contributions, technical training, or a combination of relevant experience and applied project delivery.
Day-to-Day Activities
Design, develop, test, and deploy AI agents, RAG pipelines, MCP servers, and LLM-based applications using Python and AWS services.
Collaborate with engineering, DevOps, security, architecture, and business stakeholders to define requirements, review designs, and resolve implementation issues.
Integrate AI solutions with CI/CD workflows, vector databases, application programming interfaces, code repositories, security tools, and remediation systems.
Evaluate solution performance, security, reliability, latency, cost, and response quality while making technical decisions within approved architecture and governance standards.
Qualifications
A bachelor’s or master’s degree in Computer Science, Information Technology, Engineering, Artificial Intelligence, Data Science, or a related field is preferred; equivalent relevant experience may be considered.
Minimum 8+ years of overall professional experience and at least 3+ years of relevant AI experience are required.
AWS, AI, machine learning, cloud architecture, security, or related certifications are preferred but not required where equivalent practical experience is demonstrated.
Role-relevant training in LLMs, GenAI, RAG engineering, AI agents, AWS, application security, CI/CD, and responsible AI practices is preferred.
Continuous professional development is expected through technical training, certifications, practical experimentation, knowledge sharing, and evaluation of emerging AI and cloud technologies.
Professional Competencies
Applies structured reasoning, experimentation, and evidence-based problem-solving to address AI, software, cloud, security, and integration challenges.
Works effectively with engineering, DevOps, security, architecture, and business teams to deliver reliable AI solutions and share technical knowledge.
Communicates AI architecture, risks, limitations, technical decisions, and delivery progress clearly to technical and non-technical stakeholders.
Adapts to changes in LLM capabilities, AWS services, AI frameworks, security requirements, application architectures, and delivery priorities.
Evaluates innovative AI approaches while balancing accuracy, reliability, security, privacy, maintainability, sustainability, and cost.
Plans and prioritizes development, testing, integration, documentation, incident resolution, and continuous improvement activities according to business impact and delivery commitments.
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