Agentic AI Architect

Akaasa Technologies; United States; Hybrid; USD 140,000 - 200,000; Full time

Job summary

Akaasa Technologies is seeking a senior AI architect to lead the Agentic AI Platform design. In this hybrid Fort Worth, TX role you will shape multi-agent orchestration, tool-use frameworks, and LLM integration pipelines to build production-grade systems.

You will mentor engineers, define ADRs, review architecture decisions, and collaborate with ML and software teams to ensure reliability, security, and scalable performance at airline-scale-like needs.

Qualifications

• At least 3 years designing AI/ML platform systems.
• Hands-on with LLM orchestration frameworks (LangChain, LangGraph, Semantic Kernel, or similar).
• Strong Python and at least one of Java/Go/TypeScript.
• Production experience building agentic AI systems or LLM-powered apps at scale, including prompt engineering, tool-use patterns, RAG pipelines, and observability.

Responsibilities

• Define and drive architecture for multi-agent orchestration systems.
• Design patterns for reliability, observability, and guardrails at production scale.
• Lead design reviews and ADRs.
• Collaborate with ML and software engineers to ensure scalable, secure components.
• Evaluate and integrate emerging agentic AI frameworks.
• Define API contracts, data flow patterns, and integration standards.
• Mentor engineers on production-grade AI systems.

Skills

LLM orchestration frameworks

Distributed systems design

Microservices architecture

API design REST/gRPC

Python

Java/Go/TypeScript

Agentic AI systems at scale

Observability

Tool-use patterns

Tools

Kubernetes

Cloud platforms AWS/Azure/GCP

MLOps/LLMOps tooling

Vector databases (Pinecone/Weaviate/pgvector)

Job description

Title: Agentic AI Architect

Location: Hybrid in Fort Worth, TX Need Local

Duration: 6+ Months

MOI: Skype

Need LinkedIn

Job Description:

• As Sr Eng 2 Architect on the Agentic System Layer (ASL) team, candidates will define and drive the technical architecture for clients' agentic AI platform.
• Day-to-day responsibilities include: designing and evolving the architecture for multi-agent orchestration systems, tool-use frameworks, and LLM integration pipelines; establishing patterns for agent reliability, observability, and guardrails at production scale; leading technical design reviews and producing architecture decision records (ADRs); collaborating with ML engineers and software engineers to ensure platform components are scalable, secure, and maintainable; evaluating and integrating emerging agentic AI frameworks (e.g., LangGraph, CrewAI, Semantic Kernel, AutoGen); defining API contracts, data flow patterns, and integration standards across the AI platform ecosystem; mentoring engineers on best practices for building production-grade AI systems.

Top 3 Mandatory Skills and Experience:

At least 3 years designing AI/ML platform systems, including hands-on experience with LLM orchestration frameworks (LangChain, LangGraph, Semantic Kernel, or similar).

• Deep expertise in distributed systems design, microservices architecture, event-driven patterns, and API design (REST/gRPC), with strong proficiency in Python and at least one of Java/Go/TypeScript
• Production experience building and deploying agentic AI systems or LLM-powered applications at scale, including prompt engineering, tool-use patterns, RAG pipelines, and agent reliability/observability.

Nice to Have Skills:

• Experience with Kubernetes/container orchestration, cloud platforms (AWS/Azure/GCP), MLOps/LLMOps tooling, vector databases (Pinecone, Weaviate, pgvector), knowledge graphs, airline/travel domain experience, TOGAF or similar architecture certification, experience with multi-agent system design patterns and agent evaluation/benchmarking frameworks.

Describe a great candidate that you are looking for and what skills and experience they will have:

A great candidate is a seasoned architect who has shipped production agentic AI systems - not just prototypes.

• They can whiteboard a multi-agent orchestration system, debate tradeoffs between different LLM routing strategies, and then jump into code to prove out a design.
• They understand that agentic systems at airline scale need bulletproof reliability, graceful degradation, and real observability.
• They have opinions backed by experience, they push back on bad ideas constructively, and they make the engineers around them better.