Senior Full Stack Engineer, Conversational AI, Voice Applications

This is a fully remote position, open to applicants in India.

📋 Description

• Evaluate current LMS features, reusable prototypes, and targeted extensions prior to suggesting a configured or custom solution.

• Document feasibility, dependencies, delivery efforts, and operational costs involved.

• Develop a two-way voice prototype featuring responsive audio, turn-taking, interruption handling, session state management, and failure recovery mechanisms.

• Establish an AI customer role incorporating approved facts, persona details, objections, and objectives.

• Accommodate diverse learner responses and natural conclusions without disclosing anticipated answers.

• Transform authorized training materials into configurable, version-controlled scenarios and rubrics.

• Maintain a clear distinction between customer simulation and post-session assessments.

• Explore the launch capabilities from Absorb LMS, browser microphone access, and learner identity verification.

• Validate both embedded and separate-tab fallback experiences and execute agreed-upon access and completion strategies.

• Generate evidence-based scores and balanced coaching utilizing approved weights, exclusions, and serious-error protocols.

• Calculate totals programmatically and ensure generated PDFs align with underlying results.

• Preserve records of learners, agencies, scenarios, rubrics, and attempts.

• Create branded PDFs and basic exports while maintaining structured data for future reporting integrations.

• Implement usage allowances, reset rules, alerts, and limits effectively.

• Manage simultaneous requests, retries, and failed attempts without duplicating charges or results.

• Safeguard agency data boundaries, credentials, and recordings while applying access, retention, and deletion policies.

• Deploy and sustain the application, oversee environments and secrets, monitor latency and usage, rectify defects, and hand over source code, configuration, and operational documentation.

• Conduct weekly demonstrations, keep an agreed-upon task tracker, and promptly identify blockers.

• Engage in technical discussions, content-specialist validation, scoring calibration, user testing, deployment, and handover processes.

⛳️ Requirements

• Demonstrated ownership of at least one functional two-way voice application or conversational product with spoken interaction capabilities.

• Strong frontend development experience with TypeScript and React or a comparable framework.

• Familiarity with browser audio capture and playback, asynchronous UI behavior, microphone permissions, and session error states.

• Backend development experience in Python (e.g., FastAPI) or Node.js with TypeScript.

• Proficient in REST APIs, WebSockets, and/or WebRTC integration, authentication, background tasks, and relational data modeling.

• Practical experience integrating LLM and speech services.

• Expertise in prompt and context design, structured model outputs, scenario grounding, and evaluation methodologies.

• Experience with third-party API integration, secure session management, SQL databases like PostgreSQL, PDF generation, and dependable export workflows.

• Skills in automated testing and debugging across browser, backend, and AI services.

• Proficiency in Git, code reviews, deployment pipelines, Docker or equivalent packaging, and one cloud environment.

• Strong written English communication skills.

• Ability to convert business requirements into small, testable releases and articulate assumptions and trade-offs to a non-technical project lead.

• Typically 5-8 years of experience in software engineering.

• Preference for immediate availability.

• Willingness to participate in scheduled discussions within US time zones.

• Remote work based in India; Bengaluru is preferred.

• A degree in a relevant field or equivalent practical experience is acceptable.

• Preferred: Familiarity with Absorb or other LMS; LTI 1.3, OIDC/SSO or secure external-tool launches; multi-tenant SaaS; rubric-based AI evaluation; training/coaching products; insurance workflows; document retrieval; integrations with Sheets, BigQuery, HubSpot, or Zapier; avatar integration.

🏝️ Benefits

• Paid initial assessment lasting 1-2 weeks.

• Possibility of part-time support for 3-6 months following the initial engagement.

• Scheduled discussions within US time zones with agreed overlap.

• Full-time contract capacity of approximately 35-40 hours per week during the planned engagement.