3+ years of experience as a QA / Business application developer / Business analyst in a global SAAS company. 

Proven experience designing and delivering AI-driven workflows in a SaaS environment, partnering closely with business stakeholders.

Low-code/no-code build skills and advanced prompt engineering (tool/function calling, schema-constrained outputs, JSON mode).

Hands-on with AI Gateway–style action catalogs (configure inputs/outputs, field mapping, chaining, retries, error handling), plus familiarity with platforms like Salesforce, Snowflake, Gong , ERP , Etc.

Solid SQL for analysis, feature shaping, and workflow optimization (not full data engineering).

Familiarity with the “Context Engineering” concept using API’s and MCPs.

Understanding of hallucination-mitigation strategies (retrieval grounding, instruction hierarchy, eval sets, guardrails).

Entrepreneurial, rapid prototyper who can own initiatives end-to-end and iterate based on impact.

Build, test, and deploy AI agents/automations using the AI Gateway and low-code tools; move quickly from prototype to production.
Design scalable, reliable, secure workflows (idempotency, retries, rate limits, monitoring, fallbacks).

Implement prompt patterns (tool calling, few-shot, structured outputs) with eval harnesses and canary tests.

Configure and chain prebuilt actions (no low-level REST): map fields, define inputs/outputs, set pre/post-processors, handle errors.

Use gateway-managed auth and secrets; enforce least-privilege access and data minimization.

Write SQL to shape/report data for agents and to measure workflow performance.

Partner with GTM, Marketing, CS, HR, Finance, Legal to capture requirements and translate them into shippable workflows.

Collaborate with Engineering/Data/AI and AI Platform/Integrations for net-new actions; provide specs and acceptance criteria.

Act as a trusted advisor, prioritizing use cases by impact and feasibility.

Explain complex concepts to non-technical stakeholders; drive alignment and adoption.

Document prompts, action configs, data contracts, runbooks with business and technical context.

Support training and change management to scale usage across teams.

Apply hallucination mitigation (retrieval grounding, citations, output validation, policy-aware refusals).

Instrument metrics (adoption, cycle time, accuracy, ROI) and iterate for continuous improvement.