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

Job Summary
Synechron is seeking a Senior Agentic AI / Generative AI Engineer to design, develop, and scale autonomous, production-grade AI systems.
The role will focus on building complex multi-agent orchestration frameworks and advanced Retrieval-Augmented Generation (RAG) systems using AWS Bedrock as the primary cloud foundation model platform. The engineer will work with structured and unstructured enterprise datasets to develop autonomous reasoning, planning, memory, and tool-calling workflows that safely automate complex business processes.
The position will contribute to business objectives by enabling intelligent workflow automation, improving operational efficiency, supporting reliable decision-making, and delivering secure, scalable, measurable, and maintainable AI solutions.
Software Requirements
Required Software Skills
Python: Expert proficiency for AI engineering, backend services, data pipelines, agent workflows, and production applications.
Asynchronous backend APIs: Hands-on experience with FastAPI, Flask, or equivalent Python frameworks.
AWS Bedrock: Experience deploying and scaling foundation models, including Anthropic Claude, Llama, and Mistral.
AWS Bedrock capabilities: Experience with Knowledge Bases, Agents, Guardrails, and custom model evaluations.
AWS services: Hands-on experience with EC2, Lambda, IAM, VPCs, and Step Functions.
Agent orchestration frameworks: Deep experience with LangGraph, CrewAI, AutoGen, Semantic Kernel, or comparable frameworks.
Multi-agent systems: Experience designing planners, executors, retrievers, validators, human-in-the-loop workflows, and tool-calling loops.
RAG architectures: Experience developing ingestion, chunking, embedding, metadata, retrieval, reranking, and evaluation pipelines.
Vector infrastructure: Strong understanding of semantic search mechanics, indexing algorithms, vector databases, and reranking pipelines.
Vector databases: Experience with Pinecone, OpenSearch, pgvector, Chroma, or equivalent technologies.
LLMOps: Experience with prompt versioning, log streaming, latency tracking, quality measurement, and cost optimization metrics.
AI safety: Knowledge of security guardrails, prompt-injection handling, data alignment, secure tool execution, and responsible AI practices.
Preferred Software Skills
Contributions to open-source agent libraries or Model Context Protocol (MCP) ecosystems.
Experience fine-tuning models using PEFT or LoRA techniques for specialized domain knowledge.
Familiarity with model monitoring, concept drift, data drift, automated scoring, and evaluation operations.
Experience with infrastructure as code, containerization, CI/CD, and automated deployment.
Experience designing cost-efficient, resource-efficient, and sustainable AI systems.
Version and Experience Guidance
Specific software versions are not mandated in the requirements.
Candidates should have experience with current, production-supported versions of Python, backend frameworks, AWS services, orchestration frameworks, and vector technologies.
Candidates should be able to assess compatibility, manage upgrades, maintain version control, and support production lifecycle management.
Experience should include production-level LLM and agentic AI workflows rather than only experimental or prompt-based prototypes.
Overall Responsibilities
Design and orchestrate multi-agent workflows using planners, executors, retrievers, validators, and human-in-the-loop patterns.
Implement reasoning mechanics such as ReAct, chain-of-thought, tree-of-thought, and self-reflection loops with appropriate safety and observability controls.
Develop robust memory systems using state graphs, short-term session logs, and long-term knowledge bases.
Build autonomous task-execution engines with fine-grained tool calling, API integrations, fallback strategies, validation, and escalation controls.
Deploy and scale foundation models through AWS Bedrock.
Use AWS Bedrock Knowledge Bases, Agents, Guardrails, and custom model evaluations to develop enterprise AI solutions.
Develop secure serverless backend workflows using AWS Lambda and AWS Step Functions.
Implement LLMOps practices for prompt versioning, log streaming, latency tracking, quality measurement, and cost optimization.
Architect end-to-end data-ingestion pipelines for embedding generation, chunking strategies, metadata tagging, and semantic indexing.
Develop and refine semantic search engines using vector databases and reranking pipelines.
Design evaluation datasets and data pipelines to track concept drift, data drift, response quality, and automated system scoring.
Integrate unstructured enterprise repositories with LLM applications while maintaining semantic indexing accuracy and data protection.
Translate abstract business processes into deterministic, code-driven step logic and measurable technical outcomes.
Collaborate with product, engineering, data, security, and operations teams to define requirements and delivery plans.
Participate in code reviews, provide technical guidance, and support team members with implementation and troubleshooting.
Optimize AI systems for reliability, safety, scalability, latency, maintainability, sustainability, and cost.
Maintain technical documentation covering architecture, workflows, prompts, data pipelines, evaluation methods, operating procedures, and known limitations.
Technical Skills (By Category)
Programming Languages
Essential
Expert proficiency in Python.
Experience developing asynchronous backend APIs using FastAPI, Flask, or equivalent frameworks.
Ability to write modular, maintainable, testable, and production-ready code.
Ability to develop agent tools, API integrations, data pipelines, evaluation utilities, and automation components.
Understanding of asynchronous execution, retries, error handling, logging, and workflow state management.
Preferred
Experience with additional programming languages used in cloud-native, data, or enterprise application development.
Experience developing reusable libraries and shared components for AI applications.
Exposure to event-driven and distributed application development.
Databases/Data Management
Essential
Experience working with structured and unstructured enterprise datasets.
Strong understanding of embeddings, chunking, metadata tagging, semantic indexing, retrieval, and reranking.
Experience with vector databases such as Pinecone, OpenSearch, pgvector, Chroma, or equivalent technologies.
Understanding of semantic search mechanics and indexing algorithms.
Ability to design data-ingestion pipelines for RAG applications.
Experience creating evaluation datasets and pipelines for automated scoring, data drift, and concept drift analysis.
Understanding of data quality, lineage, access control, retention, and data alignment.
Preferred
Experience with NoSQL databases and knowledge-base technologies.
Familiarity with document-processing, data lake, and enterprise repository integration patterns.
Experience with data reconciliation, archival, lifecycle management, and metadata governance.
Exposure to data preparation for model fine-tuning using PEFT or LoRA.
Cloud Technologies
Essential
Hands-on experience with AWS Bedrock.
Experience with AWS EC2, Lambda, IAM, VPCs, and Step Functions.
Understanding of secure, scalable, and highly available cloud architecture.
Experience designing serverless workflows for agent execution and orchestration.
Understanding of cloud identity, networking, service integration, monitoring, and operational support.
Ability to optimize AI workloads for latency, reliability, resource utilization, and cost.
Preferred
Experience with cloud-native deployment automation and infrastructure as code.
Familiarity with containerization and Kubernetes-based deployments.
Experience with multi-environment or hybrid cloud application delivery.
Understanding of sustainable cloud operations and efficient resource allocation.
Frameworks and Libraries
Essential
LangGraph, CrewAI, AutoGen, Semantic Kernel, or comparable agent orchestration frameworks.
AWS Bedrock Agents, Knowledge Bases, Guardrails, and model evaluation capabilities.
FastAPI, Flask, or equivalent asynchronous backend API frameworks.
Vector database and semantic search technologies.
Frameworks and libraries for embeddings, retrieval, reranking, and evaluation.
Libraries supporting tool calling, memory management, workflow state, API integration, and agent observability.
Experience implementing planning, execution, delegation, validation, reflection, routing, and human-approval patterns.
Preferred
Model Context Protocol (MCP) libraries and ecosystem integrations.
Model-serving, LLMOps, evaluation, and monitoring frameworks.
Fine-tuning libraries supporting PEFT and LoRA techniques.
Additional RAG, document-processing, and knowledge-management frameworks.

Skills
AWS, Python, React, FastAPI, Flask, Kubernetes, CI/CD, LLM, Generative AI, Documentation