AI Engineer

About RiyaLabs
RiyaLabs helps organizations move enterprise AI from experimentation to dependable, governed business execution. We build AI coworkers, coordinated AI teams, enterprise integrations, and practical controls that enable responsible AI use in real workflows.
Our offering includes:
RiyaLabs Studio: Role-defined AI coworkers and coordinated AI teams operating across approved knowledge, systems, and tools.
RiyaLabs Trust Gateway: Governance, approval, observability, and policy controls for model and tool calls.
RiyaLabs Consultants: AI strategy, architecture, implementation, integration, workflow redesign, and adoption support.
RiyaLabs Academy: Hands-on, role-based learning for leaders, business teams, and technical builders.
We are hiring an AI Engineer to design, build, evaluate, and operate practical AI solutions. This hands-on role is for an engineer who can move beyond prompts and prototypes to deliver secure, observable, maintainable AI applications.
Role Purpose
The AI Engineer will help develop RiyaLabs Studio, AI coworkers, multi-step workflows, Retrieval-Augmented Generation (RAG) systems, enterprise connectors, and client AI implementations.
You will work with product, engineering, consulting, and client-delivery teams to turn business requirements into working applications. Your work will enable grounded retrieval, approved tool use, reusable work products, human approval for consequential actions, and traceability across workflows.
Key Responsibilities:
AI Engineering
Design, build, test, deploy, and maintain AI-enabled applications and backend services using Python and approved frameworks.
Develop AI coworkers and workflow components with defined instructions, knowledge sources, scoped tools, handoffs, and approval gates.
Build conversational AI experiences that retrieve grounded answers, generate work products, and interact with approved business systems.
Implement prompt, context, memory, structured-output, and tool-use patterns appropriate to each workflow.
Develop reusable components for orchestration, document processing, retrieval, evaluation, logging, and access control.
Convert product requirements, workflow definitions, and client needs into production-quality technical solutions.

LLM, RAG, and Workflows
Build RAG systems that ingest, process, index, retrieve, cite, and evaluate information from approved enterprise sources.
Develop document-ingestion pipelines covering extraction, chunking, metadata enrichment, embeddings, indexing, retrieval, and relevance evaluation.
Integrate and evaluate LLM providers based on quality, latency, cost, safety, and customer requirements.
Build tool-calling and multi-step AI workflows with defined permissions, validation, error handling, and human-approval controls.
Create evaluation datasets, automated tests, and regression checks for grounding, relevance, tool-call accuracy, policy adherence, latency, and cost.
Ensure high-impact actions remain proposed until approved by authorized users.
Integrations and Platform Development
Build secure APIs, backend services, and integration layers for RiyaLabs products and client solutions.
Connect AI workflows with approved enterprise systems, databases, documents, APIs, and business tools.
Develop connectors using REST APIs, webhooks, service accounts, OAuth, authentication flows, and scoped permissions.
Contribute to MCP-based or equivalent integration approaches where appropriate.
Design resilient workflows with retries, idempotency, audit trails, rate-limit management, and failure recovery.
Support cloud-hosted, customer-hosted, and hybrid deployment models.
Security and Observability
Apply least-privilege access, tenant isolation, secrets management, data minimization, and secure access boundaries.
Ensure model requests, outputs, tool calls, workflow decisions, errors, latency, token usage, and cost are traceable.
Support prompt-injection defenses, input validation, output handling, PII redaction, and relevant AI-security controls.
Participate in code reviews, security reviews, threat modeling, testing, and secure-development practices.
Follow RiyaLabs standards for confidentiality, client-data handling, source-code protection, and responsible AI use.
Collaboration and Delivery
Work with product managers, solution architects, AI consultants, designers, and delivery teams.
Participate in client discovery to understand workflows, source systems, constraints, business objectives, and acceptance criteria.
Produce technical documentation, including architecture diagrams, API specifications, data-flow diagrams, test plans, deployment guides, and runbooks.
Support implementations, pilots, demonstrations, production releases, issue investigation, and reliability improvements.
Contribute reusable engineering standards, reference architectures, starter kits, and internal technical knowledge.
Required Skills
Strong Python skills and experience building production-quality backend applications.
Strong understanding of Git, code reviews, testing, debugging, documentation, CI/CD, and secure coding.
Experience with REST APIs, webhooks, JSON, authentication, and service integrations.
Experience with SQL databases such as PostgreSQL or MySQL; Redis and NoSQL familiarity is advantageous.
Familiarity with Docker, Linux, cloud deployment, and at least one major cloud platform: AWS, Azure, or GCP.
Experience using LLM APIs such as OpenAI, Anthropic, Google Gemini, Azure OpenAI, or approved open-source models.
Hands-on experience with RAG, embeddings, vector search, document processing, chunking, retrieval, reranking, and citations/grounding.
Familiarity with LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or equivalent frameworks.
Understanding of prompt engineering, structured outputs, function calling, context management, agent orchestration, and AI evaluation.
Familiarity with pgvector, Pinecone, Qdrant, Weaviate, Elasticsearch, OpenSearch, Chroma, or Azure AI Search.
Knowledge of OAuth 2.0, JWTs, RBAC, secrets management, API security, and least-privilege principles.
Awareness of AI risks including prompt injection, hallucinations, data leakage, excessive permissions, and insecure tool use.
Familiarity with observability tools such as OpenTelemetry, LangSmith, Grafana, Prometheus, Datadog, Sentry, or equivalent.
Required Experience
2–5 years of professional experience in software engineering, backend engineering, AI engineering, machine-learning engineering, or related roles.
Demonstrable experience building and shipping AI applications, LLM integrations, RAG systems, automation workflows, or intelligent assistants.
Experience with source control, testing, deployment, production support, and peer-review practices.
Ability to convert ambiguous business requirements into technical tasks and production-ready deliverables.
Strong written and verbal English communication skills.
Preferred Experience
Multi-step AI workflows, agentic systems, tool-using AI applications, or enterprise integrations.
SaaS platforms, workflow automation, data platforms, multi-tenant design, or enterprise identity/access management.
MCP, enterprise connectors, React, Next.js, TypeScript, Kubernetes, Terraform, infrastructure as code, or cloud DevOps.
AI evaluation, red-teaming, safety testing, governance controls, or model observability.
Technical portfolio, GitHub work, open-source contributions, or demonstrable AI projects.
Bachelor’s degree in Computer Science, Engineering, Data Science, AI, or a related field; equivalent practical experience is welcome.
Tools and Technology Environment
The AI Engineer will work with a practical, evolving technology stack. Experience with every tool is not required; however, the successful candidate should be comfortable learning and working across the following areas:
Pr

Work arrangement
Hybrid