Senior Full Stack Engineer (Conversational AI and Voice Applications)
New
A
Attain SolutionsConversational AI
Remote within India, Standard work timing: 3:00 PM to 12:00 AM IST; overlap with US morning and/or evening hours required.ContractSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Clear written English
- Experience
- Typically 5-8 years in software engineering; relevant delivery evidence takes priority.
- Required Skills
- DockerNode.jsPostgreSQLPythonTypeScriptWebRTCReact
Requirements
- Have proven ownership of at least one working two-way voice application or conversational product with spoken interaction.
- Be able to explain your contribution, architecture, latency, interruption handling, failure recovery and usage costs.
- Have strong frontend development experience with TypeScript and React or a comparable framework.
- Have experience with browser audio capture and playback, asynchronous UI behavior, microphone permissions and session error states.
- Have backend development experience in Python, such as FastAPI, or Node.js with TypeScript.
- Have experience with REST APIs, WebSockets and/or WebRTC integration, authentication, background work and relational data modeling.
- Have practical experience integrating LLM and speech services, using real-time speech-to-speech or speech recognition, a language model and speech synthesis.
- Understand prompt and context design, structured model outputs, scenario grounding and evaluation against approved facts.
- Have experience with third-party API integration, secure session handling, SQL databases such as PostgreSQL, PDF generation and export workflows.
- Have experience with automated testing and debugging across browser, backend and AI services, Git, code review, deployment pipelines, Docker or equivalent packaging, and a cloud environment.
- Have clear written English and be able to translate business requirements into small, testable releases and explain assumptions and trade-offs to a non-technical project lead.
- Typically have 5-8 years of software engineering experience; a relevant degree or equivalent practical experience is suitable.
Responsibilities
- Assess existing LMS capabilities, reusable prototypes and custom-solution options; document feasibility, dependencies, delivery effort and operating costs.
- Build a working two-way voice prototype with responsive audio, turn-taking, interruption handling, session state and failure recovery.
- Implement the AI customer role using approved facts, persona, objections and objectives, and support varied learner responses and natural endings.
- Convert approved training material into configurable, versioned scenarios and rubrics, keeping customer simulation separate from post-session assessment.
- Validate LMS launch, browser microphone access and learner identity; implement the agreed access and completion approach.
- Produce evidence-based scores and coaching, apply approved scoring rules, calculate totals in code and keep PDFs consistent with stored results.
- Store learner, agency, scenario, rubric and attempt records; generate branded PDFs and agreed exports while preserving structured data.
- Implement usage allowances, resets, alerts and limits; handle concurrent requests, retries and failed attempts without duplicate charges or results.
- Protect agency data, credentials and recordings; apply access, retention and deletion rules and maintain useful privacy-conscious logs.
- Deploy, maintain and monitor the application, resolve defects, and hand over source code, configuration and operating documentation.
View Full Description & ApplyYou'll be redirected to the employer's site
