AI Engineer – Agentic AI & Multi-Agent Systems | AWS Bedrock, LangChain & LangGraph

Job Summary

Synechron is seeking an AI Engineer to design, develop, and deploy enterprise-grade AI agents and multi-agent systems using modern agentic AI frameworks. The role will focus on building reliable, scalable, and secure AI-driven solutions that support business and product objectives.

The position will contribute to the full lifecycle of agentic applications, including solution design, development, orchestration, evaluation, optimization, and production deployment. The successful candidate will work closely with product and engineering teams to translate business requirements into practical AI solutions.

The role contributes to business value by improving workflow automation, enabling intelligent decision support, increasing operational efficiency, and supporting the responsible adoption of generative AI across enterprise environments.

Software Requirements

Required Software Skills

• Python: Strong hands-on development experience for AI applications, APIs, automation, and production services.
• Amazon Bedrock: Hands-on experience designing and implementing generative AI and agent-based solutions.
• AgentCore: Hands-on experience using AgentCore for AI agent development, orchestration, or deployment.
• LangChain: Expertise in building LLM-powered applications, tool integrations, chains, and agent workflows.
• LangGraph: Expertise in designing stateful, controllable, and multi-step agent workflows.
• Strands Agents SDK or similar agent framework: Practical experience developing agentic applications.
• Model Context Protocol (MCP): Experience designing or integrating MCP-based solutions.
• LLM orchestration: Strong understanding of prompt engineering, tool calling, planning, memory, routing, and workflow coordination.
• Multi-agent systems: Experience implementing systems in which multiple specialized agents collaborate to complete tasks.
• AI agent design patterns: Deep understanding of patterns for planning, reflection, delegation, routing, supervision, memory, and human-in-the-loop controls.

Preferred Software Skills

• AWS cloud services: Experience deploying cloud-native AI applications in AWS environments.
• Retrieval-Augmented Generation (RAG): Exposure to frameworks and components used to build RAG-based applications.
• Observability and evaluation tools: Familiarity with monitoring, tracing, evaluation, quality measurement, and performance analysis for AI agents.
• Productionization tools: Experience with software components and practices used to deploy, operate, and maintain generative AI applications.

Version and experience guidance: No specific software versions are mandated in the requirements. Candidates should demonstrate hands-on experience with current, organization-approved versions of the listed tools and frameworks, along with the ability to assess version compatibility, upgrades, and production support considerations.

Overall Responsibilities

• Design and develop autonomous AI agents and multi-agent workflows that address defined business and operational needs.
• Build agentic applications using Amazon Bedrock, AgentCore, LangChain, LangGraph, Strands Agents SDK, and related frameworks.
• Implement orchestration, planning, memory management, tool calling, routing, and human-in-the-loop capabilities.
• Design, develop, and integrate solutions based on the Model Context Protocol.
• Create scalable agent architectures that follow established AI agent design patterns and engineering best practices.
• Translate product and business requirements into clear technical designs, implementation plans, and measurable outcomes.
• Collaborate with product managers, software engineers, data specialists, security stakeholders, and other delivery teams.
• Evaluate and optimize LLM performance, response quality, reliability, latency, cost, and safety.
• Develop reusable components, documentation, testing approaches, and operational procedures for AI agent solutions.
• Support production deployment, troubleshooting, monitoring, and continuous improvement of AI applications.
• Apply responsible AI, privacy, security, and sustainability considerations throughout the solution lifecycle.
• Contribute to performance outcomes such as improved task completion, reduced manual effort, dependable system behavior, and maintainable production operation.

Technical Skills (By Category)

Programming Languages

Essential

• Strong Python development experience.
• Ability to write maintainable, testable, and production-ready code.
• Ability to develop integrations, APIs, automation components, and agent tools in Python.

Preferred

• Experience with additional programming languages used in cloud-native or enterprise application development.
• Experience with asynchronous programming and event-driven application development.

Databases/Data Management

Essential

• Understanding of data handling requirements for LLM applications and AI agents.
• Ability to manage structured and unstructured information used in prompts, tools, workflows, and agent memory.
• Understanding of data quality, access control, retention, and traceability considerations.

Preferred

• Exposure to vector databases or vector search technologies for RAG applications.
• Experience designing retrieval, indexing, metadata, and document-processing workflows.
• Familiarity with data stores used for conversation history, agent state, or long-term memory.

Cloud Technologies

Essential

• Hands-on experience with Amazon Bedrock.
• Hands-on experience with AgentCore.
• Understanding of cloud-based deployment considerations for AI agents, including scalability, availability, access management, and operational support.

Preferred

• Experience with cloud-native deployments on AWS.
• Familiarity with containerized services, serverless components, event-driven architectures, and infrastructure automation.
• Understanding of cloud cost management and resource optimization for AI workloads.

Frameworks and Libraries

Essential

• Expertise in LangChain.
• Expertise in LangGraph.
• Experience with Strands Agents SDK or a similar agent framework.
• Experience implementing multi-agent systems.
• Knowledge of MCP and MCP-based integrations.
• Strong understanding of prompt engineering and LLM orchestration.
• Practical knowledge of agent design patterns, including planning, delegation, routing, tool use, memory, reflection, and supervision.

Preferred

• Exposure to RAG frameworks and architectures.
• Familiarity with AI evaluation, observability, tracing, and monitoring libraries.
• Experience with frameworks that support production-grade GenAI applications.

Development Tools and Methodologies

Essential

• Experience with software development lifecycle practices, including requirements analysis, design, development, testing, deployment, and support.
• Ability to create technical documentation, solution designs, test plans, and operational runbooks.
• Experience validating agent behavior through functional, integration, regression, and quality testing.
• Ability to use measurable criteria to evaluate response quality, reliability, latency, cost, and safety.

Preferred

• Experience with CI/CD, version control, automated testing, containerization, and infrastructure-as-code practices.
• Familiarity with agile delivery methods and iterative product development.
• Experience establishing observability and operational metrics for AI agents.

Security Protocols

Essential

• Understanding of secure prompt, tool, data, and API integration practices.
• Ability to apply appropriate access controls, input validation, output validation, and protection of sensitive information.
• Awareness of risks associated with prompt injection, unauthorized tool use, data leakage, unsafe outputs, and excessive agent autonomy.
• Ability to incorporate responsible AI, privacy, reliability, and safety controls into agent solutions.

Preferred

• Experience implementing security controls in AWS-based applications.
• Familiarity with auditability, identity and access management, secrets management, encryption, and security monitoring.
• Experience defining human approval or escalation controls for higher-risk agent actions.

Experience Requirements

• Overall experience: More than 6 years of professional experience in software engineering, AI engineering, data engineering, or closely related roles.
• AI experience: At least 2 years of hands-on experience developing AI, generative AI, LLM, agentic AI, or related solutions.
• Domain-specific experience: Practical experience designing and implementing AI agents, agent workflows, tool calling, memory management, LLM orchestration, and multi-agent systems.
• Framework experience: Hands-on experience with Amazon Bedrock, AgentCore, LangChain, LangGraph, MCP, and Strands Agents SDK or comparable agent frameworks, as specified under the required skills.
• Industry preference: Experience delivering enterprise-grade, cloud-based, regulated, or operationally critical software solutions is preferred.
• Alternative experience pathways: Candidates may qualify through equivalent combinations of professional experience, substantial project-based delivery, open-source contributions, technical research, or demonstrable production implementations that cover the required capabilities.
• Outcome evidence: Candidates should be able to demonstrate contributions to working AI solutions, such as improved automation, reliable agent execution, measurable quality improvements, reduced manual effort, or successful production adoption.

Day-to-Day Activities

• Design, develop, test, and refine AI agents, multi-agent workflows, prompts, tools, memory components, and MCP integrations.
• Collaborate with product, engineering, data, security, and delivery teams through planning sessions, design reviews, stand-ups, demonstrations, and retrospectives.
• Produce technical designs, code, test results, evaluation reports, documentation, monitoring configurations, and production support deliverables.
• Make implementation decisions within the assigned scope, escalate material risks, and recommend improvements related to quality, safety, scalability, cost, security, and sustainability.

Qualifications

• Bachelor’s degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related field; equivalent relevant experience or demonstrated technical capability may be considered.
• At least 6 years of overall relevant professional experience, including at least 2 years of hands-on AI experience.
• Practical experience with Python, Amazon Bedrock, AgentCore, LangChain, LangGraph, MCP, and Strands Agents SDK or similar frameworks.
• Relevant cloud, AI, generative AI, software engineering, or professional technology certifications are preferred but not mandatory unless required for a specific assignment.
• Commitment to continuous learning through relevant training, technical experimentation, knowledge sharing, and ongoing development in agentic AI, LLMs, cloud technologies, security, and responsible AI.

Professional Competencies

• Applies structured critical thinking to analyze complex requirements, identify constraints, evaluate trade-offs, and resolve technical problems.
• Works effectively with engineering, product, data, security, and delivery teams while contributing to shared technical outcomes.
• Communicates technical concepts clearly through documentation, design discussions, demonstrations, status updates, and stakeholder engagement.
• Adapts to evolving AI frameworks, model capabilities, business requirements, and delivery conditions through evidence-based learning.
• Identifies practical opportunities to improve agent reliability, usability, safety, scalability, sustainability, and business impact.
• Manages time and priorities effectively, maintains delivery focus, communicates dependencies early, and meets agreed 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