{"id":4011640,"url":"https://alion.io/job/synechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems","title":"Agentic AI Engineer – AWS Bedrock, LangGraph, RAG & Multi-Agent Systems","company":{"id":5306,"name":"Synechron","domain":"synechron.com","url":"https://alion.io/company/synechron","size_band":"5000+","is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"A","score":96,"open_postings":25,"ghost_share":0.04,"stale_share":0.16,"repost_share":0.2,"time_to_fill_p50_days":21,"computed_at":"2026-11-11T05:49:22Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Agile","optional":false},{"name":"AI Agents","optional":false},{"name":"Amazon EC2","optional":false},{"name":"Anthropic","optional":false},{"name":"AutoGen","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"AWS Lambda","optional":false},{"name":"AWS Step Functions","optional":false},{"name":"Chain-of-Thought","optional":false},{"name":"Chroma","optional":false},{"name":"CI/CD","optional":false},{"name":"Claude","optional":false},{"name":"CrewAI","optional":false},{"name":"Embeddings","optional":false},{"name":"FastAPI","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Flask","optional":false},{"name":"Function Calling","optional":false},{"name":"Git","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"IAM","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangGraph","optional":false},{"name":"Least Privilege","optional":false},{"name":"Llama","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"LLMOps","optional":false},{"name":"LoRA","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mistral","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"OpenSearch","optional":false},{"name":"PEFT","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Reranking","optional":false},{"name":"Semantic Kernel","optional":false},{"name":"Semantic Search","optional":false},{"name":"Threat Modeling","optional":false},{"name":"LangChain","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2026-11-10T10:29:32Z","employer_posted_date":"2026-11-10","last_verified_at":"2026-11-11T15:08:56Z","board_verified":true,"closed_at":null,"days_open":1,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":1},"description":"Job Summary\nSynechron is seeking a Senior Agentic AI / Generative AI Engineer to design, develop, and scale autonomous, production-grade AI systems.\nThe 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.\nThe 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.\nSoftware Requirements\nRequired Software Skills\nPython: Expert proficiency for AI engineering, backend services, data pipelines, agent workflows, and production applications.\nAsynchronous backend APIs: Hands-on experience with FastAPI, Flask, or equivalent Python frameworks.\nAWS Bedrock: Experience deploying and scaling foundation models, including Anthropic Claude, Llama, and Mistral.\nAWS Bedrock capabilities: Experience with Knowledge Bases, Agents, Guardrails, and custom model evaluations.\nAWS services: Hands-on experience with EC2, Lambda, IAM, VPCs, and Step Functions.\nAgent orchestration frameworks: Deep experience with LangGraph, CrewAI, AutoGen, Semantic Kernel, or comparable frameworks.\nMulti-agent systems: Experience designing planners, executors, retrievers, validators, human-in-the-loop workflows, and tool-calling loops.\nRAG architectures: Experience developing ingestion, chunking, embedding, metadata, retrieval, reranking, and evaluation pipelines.\nVector infrastructure: Strong understanding of semantic search mechanics, indexing algorithms, vector databases, and reranking pipelines.\nVector databases: Experience with Pinecone, OpenSearch, pgvector, Chroma, or equivalent technologies.\nLLMOps: Experience with prompt versioning, log streaming, latency tracking, quality measurement, and cost optimization metrics.\nAI safety: Knowledge of security guardrails, prompt-injection handling, data alignment, secure tool execution, and responsible AI practices.\nPreferred Software Skills\nContributions to open-source agent libraries or Model Context Protocol (MCP) ecosystems.\nExperience fine-tuning models using PEFT or LoRA techniques for specialized domain knowledge.\nFamiliarity with model monitoring, concept drift, data drift, automated scoring, and evaluation operations.\nExperience with infrastructure as code, containerization, CI/CD, and automated deployment.\nExperience designing cost-efficient, resource-efficient, and sustainable AI systems.\nVersion and Experience Guidance\nSpecific software versions are not mandated in the requirements.\nCandidates should have experience with current, production-supported versions of Python, backend frameworks, AWS services, orchestration frameworks, and vector technologies.\nCandidates should be able to assess compatibility, manage upgrades, maintain version control, and support production lifecycle management.\nExperience should include production-level LLM and agentic AI workflows rather than only experimental or prompt-based prototypes.\nOverall Responsibilities\nDesign and orchestrate multi-agent workflows using planners, executors, retrievers, validators, and human-in-the-loop patterns.\nImplement reasoning mechanics such as ReAct, chain-of-thought, tree-of-thought, and self-reflection loops with appropriate safety and observability controls.\nDevelop robust memory systems using state graphs, short-term session logs, and long-term knowledge bases.\nBuild autonomous task-execution engines with fine-grained tool calling, API integrations, fallback strategies, validation, and escalation controls.\nDeploy and scale foundation models through AWS Bedrock.\nUse AWS Bedrock Knowledge Bases, Agents, Guardrails, and custom model evaluations to develop enterprise AI solutions.\nDevelop secure serverless backend workflows using AWS Lambda and AWS Step Functions.\nImplement LLMOps practices for prompt versioning, log streaming, latency tracking, quality measurement, and cost optimization.\nArchitect end-to-end data-ingestion pipelines for embedding generation, chunking strategies, metadata tagging, and semantic indexing.\nDevelop and refine semantic search engines using vector databases and reranking pipelines.\nDesign evaluation datasets and data pipelines to track concept drift, data drift, response quality, and automated system scoring.\nIntegrate unstructured enterprise repositories with LLM applications while maintaining semantic indexing accuracy and data protection.\nTranslate abstract business processes into deterministic, code-driven step logic and measurable technical outcomes.\nCollaborate with product, engineering, data, security, and operations teams to define requirements and delivery plans.\nParticipate in code reviews, provide technical guidance, and support team members with implementation and troubleshooting.\nOptimize AI systems for reliability, safety, scalability, latency, maintainability, sustainability, and cost.\nMaintain technical documentation covering architecture, workflows, prompts, data pipelines, evaluation methods, operating procedures, and known limitations.\nTechnical Skills (By Category)\nProgramming Languages\nEssential\nExpert proficiency in Python.\nExperience developing asynchronous backend APIs using FastAPI, Flask, or equivalent frameworks.\nAbility to write modular, maintainable, testable, and production-ready code.\nAbility to develop agent tools, API integrations, data pipelines, evaluation utilities, and automation components.\nUnderstanding of asynchronous execution, retries, error handling, logging, and workflow state management.\nPreferred\nExperience with additional programming languages used in cloud-native, data, or enterprise application development.\nExperience developing reusable libraries and shared components for AI applications.\nExposure to event-driven and distributed application development.\nDatabases/Data Management\nEssential\nExperience working with structured and unstructured enterprise datasets.\nStrong understanding of embeddings, chunking, metadata tagging, semantic indexing, retrieval, and reranking.\nExperience with vector databases such as Pinecone, OpenSearch, pgvector, Chroma, or equivalent technologies.\nUnderstanding of semantic search mechanics and indexing algorithms.\nAbility to design data-ingestion pipelines for RAG applications.\nExperience creating evaluation datasets and pipelines for automated scoring, data drift, and concept drift analysis.\nUnderstanding of data quality, lineage, access control, retention, and data alignment.\nPreferred\nExperience with NoSQL databases and knowledge-base technologies.\nFamiliarity with document-processing, data lake, and enterprise repository integration patterns.\nExperience with data reconciliation, archival, lifecycle management, and metadata governance.\nExposure to data preparation for model fine-tuning using PEFT or LoRA.\nCloud Technologies\nEssential\nHands-on experience with AWS Bedrock.\nExperience with AWS EC2, Lambda, IAM, VPCs, and Step Functions.\nUnderstanding of secure, scalable, and highly available cloud architecture.\nExperience designing serverless workflows for agent execution and orchestration.\nUnderstanding of cloud identity, networking, service integration, monitoring, and operational support.\nAbility to optimize AI workloads for latency, reliability, resource utilization, and cost.\nPreferred\nExperience with cloud-native deployment automation and infrastructure as code.\nFamiliarity with containerization and Kubernetes-based deployments.\nExperience with multi-environment or hybrid cloud application delivery.\nUnderstanding of sustainable cloud operations and efficient resource allocation.\nFrameworks and Libraries\nEssential\nLangGraph, CrewAI, AutoGen, Semantic Kernel, or comparable agent orchestration frameworks.\nAWS Bedrock Agents, Knowledge Bases, Guardrails, and model evaluation capabilities.\nFastAPI, Flask, or equivalent asynchronous backend API frameworks.\nVector database and semantic search technologies.\nFrameworks and libraries for embeddings, retrieval, reranking, and evaluation.\nLibraries supporting tool calling, memory management, workflow state, API integration, and agent observability.\nExperience implementing planning, execution, delegation, validation, reflection, routing, and human-approval patterns.\nPreferred\nModel Context Protocol (MCP) libraries and ecosystem integrations.\nModel-serving, LLMOps, evaluation, and monitoring frameworks.\nFine-tuning libraries supporting PEFT and LoRA techniques.\nAdditional RAG, document-processing, and knowledge-management frameworks.\nDevelopment Tools and Methodologies\nEssential\nExperience across the AI application lifecycle, including requirements analysis, architecture, development, testing, deployment, monitoring, and support.\nExperience developing production-level LLM and agentic AI workflows.\nExperience with Git, code reviews, technical documentation, automated testing, and release practices.\nAbility to define technical approaches, architecture, delivery plans, quality standards, and evaluation criteria.\nExperience implementing LLMOps practices, including prompt versioning, log streaming, latency measurement, quality evaluation, and cost tracking.\nAbility to create prototypes and proof-of-concept solutions and transition suitable solutions into production.\nExperience translating business processes into deterministic, code-driven workflow logic.\nFamiliarity with Agile delivery, sprint planning, daily stand-ups, reviews, and retrospectives.\nPreferred\nExperience with CI/CD pipelines, infrastructure as code, containers, and automated deployment.\nFamiliarity with experiment tracking, model monitoring, automated regression evaluation, and production alerting.\nExperience with observability, distributed tracing, operational dashboards, and incident response.\nContributions to open-source agent libraries or MCP ecosystems.\nSecurity Protocols\nEssential\nKnowledge of implementing AI security guardrails and safe tool-calling controls.\nUnderstanding of prompt-injection risks, data leakage, unauthorized tool use, unsafe outputs, and excessive agent autonomy.\nAbility to apply data-access controls, identity management, secrets protection, and least-privilege permissions.\nUnderstanding of secure API communication, input validation, output validation, and controlled execution.\nExperience checking data alignment, retrieval accuracy, source relevance, and response safety.\nAbility to apply responsible AI principles throughout the design, development, evaluation, and deployment lifecycle.\nPreferred\nExperience with threat modeling for AI agents and LLM applications.\nFamiliarity with privacy-preserving AI, model security, auditability, and compliance controls.\nExperience implementing human approval, escalation, and review processes for higher-risk actions.\nKnowledge of security validation within LLMOps, CI/CD, and cloud deployment workflows.\nExperience Requirements\nOverall experience: 3-5+ years of experience in core software development, AI engineering, backend engineering, or a related technical role.\nAgentic AI experience: At least 1-2 years exclusively focused on production-level LLM and agentic AI workflows.\nTechnical experience: Expert Python experience with asynchronous APIs, agent orchestration, AWS Bedrock, RAG, vector infrastructure, and cloud services.\nArchitecture experience: Experience designing multi-agent systems, autonomous task-execution engines, memory systems, tool-calling workflows, and secure API integrations.\nData experience: Experience with structured and unstructured data, ingestion pipelines, embeddings, semantic search, metadata, evaluation datasets, and data-quality controls.\nSafety experience: Knowledge of security guard...","description_format":"text","description_chars":16537,"description_truncated":true,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["Continuous learning","Equity","Flexible schedule","Professional development"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Financial Software & Embedded Finance","IT Consulting & Digital Transformation","Cloud Consulting & Migration","Data Engineering & Migration Services"],"lifecycle":[{"event":"open","at":"2026-11-10T10:29:32Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":21,"reasons":["conf:1","win:early","comp:brand"],"computed_at":"2026-11-11T05:49:22Z"},"pay":null,"html_url":"https://alion.io/job/synechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems","json_url":"https://alion.io/job/synechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems.json","meta":{"generated_at":"2026-11-11T19:18:29Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":37282,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-12T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":5306},"rest":"https://alion.io/mcp/rest/get_company?id=5306"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsynechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fsynechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fsynechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/synechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsynechron-agentic-ai-engineer-aws-bedrock-langgraph-rag-multi-agent-systems"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4011640}},{"tool":"search_jobs","arguments":{"company":"synechron.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4011640},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}