Sierra and Google Developers

Band B1 / B2 - Sierra Engineer

Experience

4 6 years total in Conversational AI / agentic or virtual-assistant development (e.g., Dialogflow CX, Amelia, Kore.ai, Rasa, LLM-based agents).

1 2 years hands-on Sierra, with at least one delivered/production Sierra project.

Strong programming background in TypeScript / JavaScript.

Core Responsibilities

Build and validate agents in Agent Studio using Journeys, Conditions, Rules, Policies, Tools, and Configuration.

Implement code-defined agent behaviour in the Agent SDK (TypeScript/JSX on Sierra's custom runtime) using hooks, tool registration, and lifecycle events.

Author instruction-driven and scenario-based simulations (Studio and code) and keep them stable and meaningful.

Integrate agents with APIs and enterprise/contact-centre systems, including transfer/routing to queues and numbers with attached data.

Participate in workspace-based development: merge requests, snapshots, and workspace reviews.

Execute releases under guidance, respecting critical-simulation gates and approvals.

Contribute to CI/CD (e.g., GitHub Actions) - running simulations and wiring release checks.

Mandatory Skills (per Sierra platform)

Agent Studio: conversational design, customer journeys, and the block-based editor (Journeys, Conditions, Rules, Policies, Tools, Configuration).

Agent SDK: TypeScript/JavaScript with JSX; SDK APIs (hooks, tool registration, lifecycle events); code-defined simulations; workspace/snapshot/release concepts.

Simulations: writing instruction-driven and scenario-based tests; critical-simulation enforcement; stabilising flaky simulations.

Git & CI/CD: branching, merging, code reviews; running simulations and release enforcement in pipelines.

Good to Have

Ghostwriter (AI-assisted authoring): prompting, reviewing, validating, and merging AI-generated journeys/simulations.

Basic observability (traces/alerts) and analytics (CSAT, resolution/containment rate).

Contact-centre / IVR and telephony transfer (Genesys or similar) exposure.

Band C1 / C2 - Senior Sierra Engineer / Lead

Experience

Minimum 9 years total in Conversational AI / agentic-bot design and delivery, including solution/technical leadership.

1 2 years hands-on Sierra with a senior/lead contribution on at least one Sierra project (Sierra is new; depth is valued over tenure).

Proven full-stack engineering in TypeScript/JavaScript and enterprise SDLC.

Core Responsibilities

Own end-to-end agent/solution architecture on Sierra: agent/skill decomposition (Root and sub-agents), guardrails, tool contracts, state and context model, and orchestration.

Define integration contracts (auth, APIs, telephony/transfer, attached data) and failure-handling strategy.

Own the LLD - detailed journey/intent flows, tool contracts, state/context model, prompt/instruction design, error/edge-case handling, routing/transfer logic.

Set standards for simulation coverage, critical-simulation gates, and test strategy across the team.

Own release management: workspace reviews, merge governance, snapshot/release scheduling, approvals, and release APIs for automation.

Design and govern Git migration and CI/CD pipelines (e.g., GitHub Actions) with simulation and release enforcement.

Establish observability (monitoring, alerts, trace export to Datadog/Honeycomb) and drive analytics-based optimisation and experiments.

Ensure security and compliance: API-token and permission management, secure external integrations, and adherence to enterprise controls.

Mentor B-band engineers, run code/design reviews, and interface with client stakeholders.

Mandatory Skills (per Sierra platform)

All B-band mandatory skills, at an advanced/lead level.

Release Management: workspace development, merge requests, snapshots, release workflows (scheduling, approvals, critical-simulation gates), and release APIs for CI/CD.

Git Migration & CI/CD: strong Git and migrations; building pipelines; wiring simulation runs and release enforcement end-to-end.

Quality & Observability: monitoring/alerts, trace export (Datadog/Honeycomb), agent documentation, comprehensive simulation coverage.

Security & Compliance: Sierra security/compliance model, token/permission management, secure integration with external systems.

Good to Have

Advanced Ghostwriter usage and review governance for AI-generated changes.

Analytics & optimisation: interpreting CSAT, resolution/containment, running experiments and reporting.

BFSI / healthcare regulated-environment delivery experience.

5. Qualifications & Soft Skills

Bachelor's in Computer Science / Engineering or equivalent practical experience.

Strong problem-solving, debugging, and comfort with discovery-driven, evolving scope.

Clear written and verbal communication for design docs, reviews, and client interaction.

Ownership mindset across build test release monitor.

Job description: GECX Developer

Key Skills:

Python

Python Programming (Advanced):. You must be proficient in Python, utilizing object-oriented programming, modern type hinting, and asynchronous patterns.

Environment & Dependency Management: Familiarity with modern Python package managers like uv, virtual environments (.venv), and pip.

Command Line Interface (CLI) Proficiency: Ability to navigate CLI tools, as well as general shell scripting

Conversational AI / Agent Architecture (Dialogflow CX)

Generative Agent Design: Shifting from legacy intent-based state machines to generative, goal-oriented architectures (understanding Apps, Agents, Sub-agents, and Sessions within CX Agent Studio).

Prompt Engineering & Context Management: Writing robust system instructions, managing conversational memory, and optimizing LLM context windows for voice interactions.

Dialogflow CX Fundamentals: Understanding the underlying mechanics of Dialogflow CX.

Google Cloud Platform (GCP)

Cloud Compute & Serverless: Deploying agent components, webhook integrations, or backend APIs using Google Cloud Functions or Cloud Run.

Gcloud CLI Mastery: Utilizing gcloud for project configuration and authenticating environments via application-default credentials.

API Integration & Tool Building

Tool Calling / Function Calling: Designing and registering external APIs ("Tools") that the LLM can invoke to retrieve data, execute backend tasks, or interact with external services.

Data Handling & Payload Parsing: Using utility functions to handle pagination, flatten API responses, and convert complex Protocol Buffers (Protos) into usable data.

Testing, Evaluation & CI/CD

Automated Agent Evaluation (Evals): Creating and orchestrating "Golden tests" and automated simulation runs using SCRAPI's evals module.

Performance Metrics Tracking: Extracting, analyzing, and optimizing agent performance metrics (like real-time latency), which is highly critical for voice voice interactions.

Agentic IDE workflows: Using LLM-assisted development tools (like Gemini CLI or Claude Code) as integrated into the SCRAPI workflow to speed up agent scaffolding and debugging.