Agentic AI Lead/Architect

ABOUT SYNERGECH

Synergech Technology Solutions Inc. is a AI-native technology company building enterprise-grade AI platforms and intelligent engineering solutions. We are building an AI-native engineering and technology services model focused on transforming how enterprises build, modernize, and operate software systems — delivering intelligent automation, AI-powered workflows, and platform-level AI capabilities to clients in the insurance and financial services sectors.

Our flagship products — IntelliDoc (AI-powered document intelligence) and Infra0 (GenAI-driven cloud infrastructure provisioning) represent our commitment to building category-defining AI solutions. We are actively transforming into a fully AI-enabled workforce, embedding AI across engineering, delivery, and operations.

KEY RESPONSIBILITIES

Agentic Workflow Design & Development

• Architect and implement multi-agent systems using frameworks such as LangGraph, Semantic Kernel, AutoGen, or CrewAI

• Design agent orchestration patterns including task decomposition, tool use, context management, memory, and human-in-the-loop (HITL) flows

• Build reliable agentic pipelines handling document extraction, reasoning, routing, and structured output generation

• Implement emerging agentic protocols including MCP (Model Context Protocol), Agent-to-Agent (A2A), AG-UI, and CodeAct Code Interpreter patterns

• Design and evaluate agent skills, manage agent harnesses, and maintain agent capability registries

• Design AI solutions capable of leveraging multiple LLM ecosystems including Azure OpenAI, OpenAI, Anthropic Claude, and open-source models based on workload characteristics, governance requirements, and cost/performance considerations

Full-Stack AI Application Engineering

• Build full-stack AI-native applications using React with streaming agent interactions, AG-UI components, and HITL design patterns

• Implement real-time agent communication interfaces with streaming output, MCP elicitation flows, and event-driven notifications

• Design and expose REST APIs and webhook integrations for agent-to-system and system-to-system interactions

Azure AI Platform Engineering

• Deploy and manage AI workloads on Azure AI Foundry, Azure OpenAI Service, Azure Machine Learning, and AKS

• Design event-driven and serverless architectures leveraging Azure Functions, Event Grid, Service Bus, and Azure API Management

• Build scalable, resilient, cost-efficient cloud architectures aligned with Azure Solutions Architecture best practices

• Implement Infrastructure as Code (IaC) using Terraform; establish pipeline-as-code and policy-as-code practices across CI/CD workflows

• Containerize AI workloads using Docker and Kubernetes for portable, scalable deployment

LLM Integration & Enterprise Reliability

• Lead prompt engineering, evaluation, and optimization strategies for OpenAI GPT models, Anthropic Claude, and Azure-hosted models

• Implement RAG architectures using vector databases (Azure AI Search, PostgreSQL pgvector, Cosmos DB) and design extensible, evolvable schema and ontology models

• Focus on making enterprise AI systems reliable, accurate, controllable, and production-ready — especially when working with LLMs like OpenAI GPT models or Anthropic Claude models

• Design guardrails, output validation layers, and hallucination mitigation patterns for high-stakes enterprise workflows

Data Architecture — Relational, NoSQL & Graph

• Design and work across relational databases (PostgreSQL, SQL Server), NoSQL stores (Cosmos DB, MongoDB), and graph databases for knowledge graph and ontology-driven AI use cases

• Model extensible, evolvable schemas and domain ontologies that support AI reasoning, entity resolution, and semantic retrieval

Security & Identity

• Implement enterprise-grade security across AI systems: OAuth 2.0, Azure IAM, role-based and fine-grained access control (FGAC), managed identities, and credentials management

• Apply Azure security policies, RBAC, and least-privilege principles to AI platform components and agentic workflows

• Ensure secure handling of credentials, API keys, and secrets using Azure Key Vault and secure secrets management practices

AI-Native Engineering Practices

• Drive AI-assisted software engineering practices across the SDLC using copilots, autonomous coding agents, spec-driven development, and reusable engineering skills

• Leverage coding agents effectively across all SDLC phases — from requirements and design through development, testing, and deployment

• Help establish AI fluency standards and engineering productivity patterns across teams

• Contribute to internal AI accelerators, engineering frameworks, and delivery automation capabilities

• Enable engineering teams to effectively collaborate with AI systems while maintaining quality, governance, and reliability

Enterprise Governance & Responsible AI

• Implement responsible AI controls including observability, auditability, security, prompt protection, PII handling, and human oversight mechanisms

• Design enterprise-safe AI systems with governance, compliance, and reliability considerations built in from the ground up

• Establish patterns for AI system transparency, explainability, and accountability in regulated industry contexts

Technical Leadership & Modern Delivery

• Define AI engineering standards, design patterns, and best practices across the engineering organization

• Lead architecture reviews, code reviews, and technical roadmap planning for AI platform capabilities

• Mentor mid-level and junior engineers; foster a culture of AI-native engineering excellence

• Operate effectively in fast-moving, iterative AI delivery environments where experimentation, rapid prototyping, and production hardening coexist

• Balance innovation speed with engineering rigor, scalability, and maintainability

• Communicate complex AI concepts clearly to both engineering and business stakeholders

• Engage confidently with enterprise clients, architecture teams, and delivery leadership to shape AI solution direction

REQUIRED QUALIFICATIONS

Agentic AI & LLM Engineering

• 7+ years of software engineering experience with 3+ years in AI/ML or LLM-based systems

• Hands-on experience building production-grade agentic or multi-agent AI workflows

• Proficiency with GenAI agentic frameworks: LangGraph, Semantic Kernel, AutoGen, CrewAI, or LangChain

• Working knowledge of agentic protocols: MCP (Model Context Protocol), A2A (Agent-to-Agent), AG-UI, and CodeAct/Code Interpreter patterns

• Strong experience with context management strategies, agent skill design, agent evaluation, and agent harness construction

• Proficiency with OpenAI APIs (GPT-4o, function calling, Assistants API) and Anthropic Claude APIs

• RAG pipeline design: vector databases (Azure AI Search, PostgreSQL pgvector, Cosmos DB), chunking, embedding, and retrieval strategies

• Ability to pivot across agentic framework approaches and managed agent platforms as the ecosystem evolves

Full-Stack & API Engineering

• Full-stack experience with React; ability to build streaming agent interaction UIs, AG-UI components, and HITL design patterns

• Strong REST API and webhook design and implementation skills

• Proficiency in Python (intermediate level) and TypeScript for AI application and backend development

Cloud, Infrastructure & Architecture

• Strong Azure platform experience: Azure AI Foundry, Azure OpenAI, Azure ML, AKS, Azure Functions, API Management, Event Grid, Service Bus

• Infrastructure as Code using Terraform; pipeline-as-code and policy-as-code practices in CI/CD workflows

• Proficiency with containers (Docker, Kubernetes) for scalable AI workload deployment

• Ability to design and implement scalable, resilient, cost-efficient architectures on Azure

• Event-driven architecture and serverless architecture design and implementation

• Azure Solutions Architecture understanding across compute, networking, storage, security, and AI tiers

Data & Schema Design

• Experience with relational databases (PostgreSQL, SQL Server), NoSQL (Cosmos DB, MongoDB), and graph databases

• Ability to design extensible, evolvable schemas and domain ontologies that support AI reasoning and semantic retrieval

Security & Identity

• OAuth 2.0 implementation and Azure IAM/RBAC: permissions, policies, managed identities, and fine-grained access control (FGAC)

• Secure credentials management using Azure Key Vault and secrets management best practices

• Security-first mindset for AI systems: prompt protection, PII handling, data boundary enforcement

Engineering Practices

• Demonstrated ability to leverage coding agents and spec-driven development across all SDLC phases

• Strong GitHub Copilot and AI-assisted development tooling proficiency

• Experience leading technical teams and influencing engineering practices at an organizational level

NICE TO HAVE

• Experience designing and deploying Engineering Agent Skills that work alongside domain SMEs in human-AI collaborative workflows

• Wholesale insurance domain understanding: submission processing, broker/carrier workflows, market access, and underwriting operations

• Hands-on experience transitioning from custom agentic frameworks to managed agent platforms (Azure AI Agent Service, OpenAI Assistants, etc.)

• Experience with Databricks, MLflow, or Azure Databricks for data and model pipelines

• Prior work on document intelligence platforms (OCR, extraction, classification, IDP pipelines)

• Azure certifications (AI-102, DP-100, AZ-305) or relevant cloud AI credentials

• Contributions to open-source AI frameworks or published technical writing

• Experience working in startup or high-growth engineering environments

• Passion for AI-native engineering transformation and modern software delivery practices