Job Description

We build AI agents that actually work in enterprise environments — not prototypes, not demos. We need engineer's who can own the entire agent stack: a production frontend, a robust backend, a properly secured API and identity layer, a memory architecture that scales, and LLM integrations that are model-agnostic and built to last.

You'll be deployed on client engagements as the lead technical architect and builder of agentic systems running in AWS, OCI, and Azure. You'll work directly with client stakeholders, translate complex requirements into working systems, and leave behind infrastructure clients can operate and extend. You'll also help Trilagen productize our delivery approach as we scale the practice.

If you've only ever built agents that run on your laptop, this isn't the role. If you've shipped agentic systems into production cloud environments and know exactly what breaks and why — we want to talk.

What you'll own

Full-stack agent development  You design and build the entire application — not just the AI layer. This means a React or Next.js frontend with streaming, real-time agent UX; a Python or Node.js backend that orchestrates agent logic, manages state, and exposes clean APIs; and containerized, cloud-deployed services that operations teams can actually run. You own the repo, the CI/CD pipeline, the deployment, and the runbook.

Multi-cloud deployment  Production agent systems on all three major clouds: AWS (Lambda, ECS/Fargate, Bedrock, API Gateway), Oracle OCI (OKE, Functions, AI Services), and Azure (AKS, Azure OpenAI Service, Azure Functions). You understand the tradeoffs between platforms and can advise clients on where to run what and why.

LLM integration and model strategy  You have deep, hands-on experience with the leading LLM providers and their APIs — Anthropic Claude (Messages API, tool use, streaming, context management), OpenAI (GPT-4o, Assistants API, function calling), and Google Gemini (Gemini Pro/Flash, Vertex AI). You architect model-agnostic integration layers so clients aren't locked in, and you know how to select, swap, and benchmark models for specific agent tasks.

Agentic architecture  You understand how to design systems that do real multi-step work: tool use and function calling patterns, ReAct and plan-and-execute loops, agent-to-agent orchestration and handoffs, human-in-the-loop checkpoints, retry and failure recovery strategies, and cost/latency optimization across long-running agent workflows. Frameworks like LangGraph, CrewAI, AutoGen, and the Model Context Protocol (MCP) are tools in your toolbox, not the ceiling of your knowledge.

Memory and context layer  You've designed and implemented memory architectures for production agents: short-term conversational context, long-term persistent memory, RAG pipelines with vector databases (Pinecone, pgvector, OpenSearch, Weaviate), semantic search, and hybrid retrieval strategies. You know when to use each and how to keep them performant at scale.

Security and identity layer  This is non-negotiable for our client base. You build the security envelope around every agent system you ship: OAuth 2.0 / OIDC authentication flows, API key lifecycle management, role-based access control enforced within agent workflows, secrets management (AWS Secrets Manager, Azure Key Vault, OCI Vault), audit logging for agent actions, prompt injection defense, and data residency controls. Familiarity with Okta or SailPoint ISC is a direct advantage on our engagements.

Requirements

• 4+ years of software engineering experience with at least 2 years building and shipping LLM-powered or agentic applications in production cloud environments
• Hands-on depth with at least two of the three major LLM providers: Anthropic Claude, OpenAI, and Google Gemini — at the API level, not just via wrappers
• Full-stack proficiency: Python (FastAPI, Flask, or similar) backend, React or Next.js frontend, REST and WebSocket API design
• Production experience on at least two of: AWS, Azure, OCI — with real deployments, not sandbox accounts
• Demonstrated ability to design and implement agent memory and retrieval systems using vector databases and RAG
• Strong command of AI security practices: auth, RBAC, secrets management, audit logging, and prompt-level safeguards
• Consulting DNA — you can run a discovery session, write a technical design doc, manage client expectations, and own delivery end to end

Nice to have

• Experience with all three LLM providers (Anthropic, OpenAI, Gemini) and model-agnostic orchestration patterns
• Okta and/or SailPoint ISC integration experience
• Cloud certifications: AWS Solutions Architect, Azure Solutions Architect, OCI Architect

Benefits

Benefits:

• 401K
• Health Insurance
• Dental Insurance
• Paid Time Off
• Paid Sick Leave

Job Tags

Similar Jobs