AI Architect

The Mission: Engineering the Intelligent Enterprise

We are architecting the next generation of AI infrastructure systems that don't just process

data, but reason over it, learn from it, and act on it autonomously.

The industry is at an inflection point: shifting from rule-based automation to agentic, selfdirected AI systems capable of making decisions at enterprise scale. We are building the

specialized AI backbone combining large language models, multi-agent orchestration, and

cloud-native infrastructure to make this transition real for our clients.

We aren't looking for prompt-wrappers or tool-integrators. We are looking for architects

who want to design the cognitive layer of this new ecosystem. The foundation is being laid

now. If you prefer solving deep problems in model reliability, system observability, and

agentic reasoning this is the environment you've been looking for.

Core Responsibilities

• Architecture & System Design: Own the end-to-end design of AI and GenAI systems

from data ingestion and vector indexing to model deployment and inference

optimization. Architect scalable LLM/RAG pipelines, multiagent workflows, and

generative AI services reusable across client domains. Define enterprise standards for

embeddings, prompt orchestration, caching layers, and evaluation pipelines.

• MLOps & Production Deployment: Establish repeatable patterns for fine-tuning and

deploying ML/LLM models in production. Drive automation through MLOps and

AIOps pipelines using MLflow, Kubeflow, Airflow, and KServe. Architect for multicloud scalability across Azure, AWS, and GCP. Build strategic PoCs to validate model

fitment and translate business problems into working AI systems.

• Governance, Security & Compliance: Define and enforce AI architecture principles,

security policies, and responsible AI guardrails. Implement controls for PII/PHI

protection, hallucination risk mitigation, audit logging, and model explainability.

Apply zero-trust principles private networking, API gateways, and identity

management to keep data within secure perimeters.

• Collaboration & Technical Leadership: Partner with data engineering, cloud, security,

and product teams for end to end architectural alignment. Lead build-vs-buy

assessments for AI platforms, vector databases, and MLOps tooling. Mentor

engineers, conduct architecture reviews, and track the evolving AI landscape to

recommend timely adoption of emerging tools.

Technical & Professional Qualifications

• AI Architecture Experience: 5–10 years in software/AI engineering, platform

engineering, or cloud architecture, with at least 3–4 years hands-on in production

GenAI or LLM systems.

• LLM & Agent Framework Expertise: Deep hands-on experience with LangChain,

LlamaIndex, AutoGen, or OpenAI Agents API, with a proven ability to build and

deploy multi-agent systems at scale.

• MLOps & Engineering Depth: Strong command of MLflow, Kubeflow, Airflow, KServe,

Docker, and Kubernetes. Solid Python skills and distributed systems design

experience across Azure, AWS, and GCP.

• Vector & Search Proficiency: Hands-on experience with vector databases Pinecone,

FAISS, Chroma DB, Weaviate, or Elasticsearch and strong understanding of RAG

patterns and embedding strategies.

• Analytical Thinking: Ability to evaluate foundation model trade-offs, define finetuning strategies, and translate complex business problems into scalable AI

architectures.

• Governance & Security Knowledge: Strong grasp of data governance, PII/PHI

handling, OAuth 2.0, zero-trust architecture, and responsible AI frameworks

applicable to enterprise environments.

• Soft Skills: Clear, structured communication with both engineering teams and nontechnical stakeholder's product managers, founders, and client-facing teams with a

focus on transparency and sound technical judgment.

Good to Have

• Prior experience building AI features within a SaaS product, ideally in fintech,

accounting, or ERP domains.

• Familiarity with accounting concepts — general ledger, reconciliation, chart of

accounts, AP/AR workflows.

• • Experience with QuickBooks, Xero, Zoho Books, or similar platforms that SaaSant
• integrates with.
• • Knowledge of LLMOps, model observability (Datadog, Grafana, OpenTelemetry), and
• cost optimization for inference at scale.
• • Hands-on experience with Azure AI Foundry, AWS SageMaker, or GCP Vertex AI in a
• product context.
• Tech Stack
• • LLM & Agentic Stack: LangChain/LangGraph, OpenAI/Anthropic APIs, Pydantic AI,
• Langfuse (observability), and VectorDB (Pinecone/Chroma).
• • Deep Learning & Research Stack: Python, PyTorch, Hugging Face Transformers,
• NumPy.
• • Enterprise Production Stack: Python, TensorFlow/Keras, Docker, Kubernetes, AWS
• SageMaker/Vertex AI.
• • Data & Analytics Stack: Apache Spark (Databricks), Pandas, SQL, Kafka