Orbio AI

About Orbio

Orbio is an AI-native human capital management platform building a Digital Workforce for HR.

We design and deploy agentic systems that take ownership of operational execution across hiring, onboarding, and employee operations — while keeping humans in control.

We work with large, complex organizations across sectors such as staffing, retail, hospitality, and healthcare. Our customers operate at high volume and rely on Orbio to reduce operational friction, improve speed and quality, and scale their teams without proportional headcount growth.

Orbio is not a system of record. We sit on top of existing HR systems and own the execution and coordination layer — where day-to-day work actually happens.

Position Overview

Orbio is looking for a backend-focused Python engineer to take on a Tech Lead role and help build our conversational, agentic AI platform.

As a senior / founding-level engineer, you will play a key role in architecting and scaling intelligent workflow systems that support hiring, onboarding, and employee experiences in real enterprise environments.

You will help build an end-to-end, production-grade B2B platform with a strong focus on LLMs, autonomous agents, and conversational AI, defining core technical foundations that will scale across customers and markets.

What You'll Do

1. Set technical strategy and architectural direction for the platform
2. Drive technical decisions balancing innovation with production reliability
3. Collaborate with product and business stakeholders to translate requirements into technical roadmaps
4. Hands-on contribution to critical systems while scaling the team
5. Lead, mentor, and grow a high-performing engineering team
6. Establish engineering best practices, code quality standards, and development processes

All the desired Technical Skills we are looking for

Python expertise

1. Async programming, API development, real-time ASGI, Django/Channels
2. Testing, logging, monitoring, performance optimization
3. Production-grade application development
4. Knowledge of data storage solutions (both SQL and NoSQL)
5. Async message queues (Celery + RabbitMQ / Redis)
6. Experience with high-throughput, low-latency systems

LLMs usage

1. Strong understanding of LLMs, prompt engineering, chaining, caching and model fine-tuning
2. Experience with both open-source and closed-source LLMs
3. Experience with Retrieval-Augmented Generation (RAG) and vector databases
4. Experience with LLM frameworks such as LlamaIndex
5. Understanding of model evaluation metrics and performance benchmarks
6. LLM cost-optimisation strategies
7. LLM guardrails and security best practices

Agentic AI development

1. Experience with agentic frameworks and agent design patterns
2. Implementation of planning and reasoning systems
3. Multi-agent architectures and agent orchestration/delegation
4. Tool implementation and function calling (API wrapper, validation, error handling)
5. Context management and long-term knowledge preservation
6. Multi-agent evaluation and testing (consistency, performance, reliability)

Conversational AI

1. Using STT and TTS models
2. Managing turn-talking / interruption (voice activity detection)
3. Telephony systems (Twilio, IVR) implementation with focus on latency optimization
4. Voice interface design and conversation flow architecture
5. LLM interaction including function calling
6. Conversation memory management and context preservation (+ RAG)
7. Multi-modal conversation handling (voice, text, visual inputs)
8. Implementation of fallback strategies and graceful degradation

Full-Stack & DevOps

1. Full-stack experience with JavaScript frameworks (React preferred)
2. CI/CD pipelines
3. Cloud platforms (AWS/GCP/Azure)
4. Deploying and scaling AI systems in production

Leadership Experience

1. Experience defining technical roadmaps and architecture
2. Strong communication skills across technical and non-technical stakeholders
3. Startup or high-growth environment experience preferred
4. Track record of leading and growing engineering teams

What Success Looks Like at Orbio

1. Core backend and agentic systems run reliably in production at enterprise scale
2. AI workflows meaningfully reduce operational friction for customer teams
3. The platform compounds: new deployments get faster and more robust over time
4. Technical foundations support autonomy, observability, and safe decision-making
5. Engineering velocity stays high without sacrificing reliability

Culture at Orbio

Orbio is a high-bar, high-intensity environment. We optimize for impact, speed, and ownership — not comfort.

We operate as one team, with a flat structure and extreme ownership. We ship fast, learn from production, and challenge each other directly because we care about building something that lasts. Titles matter less than outcomes. Customers come first. Momentum matters.

About Orbio

Orbio is an AI-native human capital management platform building a Digital Workforce for HR.

We design and deploy agentic systems that take ownership of operational execution across hiring, onboarding, and employee operations — while keeping humans in control.

We work with large, complex organizations across staffing, retail, hospitality, and healthcare. Our customers rely on Orbio to reduce operational friction, improve speed and quality, and scale their teams without proportional headcount growth.

Orbio is not a system of record. We sit on top of existing HR systems and own the execution and coordination layer — where day-to-day work actually happens.

Position Overview

Orbio is looking for an AI Agent Engineer to build, operate, and continuously improve the reliability of our agentic AI systems in production.

In this role, you will focus on how agents behave, decide, fail, recover, and scale in real enterprise environments. Your work will ensure that LLM-powered agents are observable, testable, cost-efficient, and trustworthy when handling real operational workflows.

You will help build an end-to-end, production-grade B2B platform with a strong focus on LLMs, autonomous agents, and conversational AI, contributing to the technical foundations that scale across customers and use cases.

All the desired Technical Skills we are looking for

Agent Testing & Evaluation

1. Building agent evaluation pipelines (consistency, accuracy, reliability)
2. Designing test harnesses for non-deterministic systems
3. Regression testing for prompt and model changes
4. Synthetic data generation for agent testing
5. Performance benchmarking and latency profiling

Agent Monitoring & Operations at Scale

1. Observability for agent systems (tracing, logging, metrics)
2. Cost tracking and optimization across model calls
3. Alerting on agent failures, hallucinations, and degraded performance
4. Debugging complex multi-step agent behaviors in production
5. Guardrails, safety layers, and graceful degradation strategies

LLM Expertise

1. Prompt engineering, chaining, and caching strategies
2. RAG pipelines and vector databases
3. Model selection, fine-tuning, and cost optimization
4. Understanding of evaluation metrics and benchmarks

Python & Backend

1. Async programming, Django/Channels, real-time ASGI
2. Production-grade application development
3. Message queues (Celery + Redis) and high-throughput systems
4. Testing, logging, and performance optimization

Conversational AI

1. Voice pipelines: STT, TTS, turn-taking, interruption handling
2. Telephony integration (Twilio) with latency optimization
3. Conversation flow design and fallback strategies

Full-Stack & DevOps

1. Frontend experience (React preferred)
2. CI/CD pipelines and cloud deployment (AWS/GCP)
3. Deploying and operating AI systems in production

What Success Looks Like at Orbio

1. Agents behave consistently and predictably across customers and workflows
2. Failures, edge cases, and degraded behavior are detectable and recoverable
3. Agent performance, latency, and cost are measurable and actively optimized
4. New agent capabilities ship safely without breaking existing behavior
5. Customer trust in autonomous workflows increases over time

Culture at Orbio

Orbio is a high-bar, high-intensity environment. We optimize for impact, speed, and ownership — not comfort.

We operate as one team, with a flat structure and extreme ownership. We ship fast, learn from production, and challenge each other directly because we care about building systems that hold up under real-world complexity. Titles matter less than outcomes. Customers come first. Momentum matters.