Senior Full Stack Engineer (Conversational AI and Voice Applications)

Company Description

Attain Solutions provides software development, implementation, quality assurance and support services for international clients. We are seeking a hands-on senior engineer to assess and deliver a voice-based practice capability for a US training business serving insurance agencies.

In the proposed experience, the AI plays a customer throughout a short conversation. The learner speaks naturally, while the customer raises a relevant concern, responds to questions and keeps its facts and character consistent. After the session, a separate assessment produces scores and a coaching PDF. The first scope is a personal-lines and commercial-lines pair, using client-approved content.

Job Description

What you will own

- Assess existing LMS capabilities, reusable prototypes and focused extensions before recommending a configured or custom solution. Document feasibility, dependencies, delivery effort and operating costs.

- Build a working two-way voice prototype, including responsive audio, turn-taking, interruption handling, session state and recovery from common failures.

- Implement the customer role with approved facts, a persona, objections and an objective. Support varied learner responses and natural endings without feeding the learner the expected answers.

- Convert approved training material into configurable, versioned scenarios and rubrics. Keep the customer simulation separate from post-session assessment.

- Investigate launch from Absorb LMS, browser microphone access and learner identity. Validate an embedded experience and a separate-tab fallback; implement the agreed access and completion approach. 

Engineering responsibilities

- Produce evidence-based scores and balanced coaching. Apply approved weights, exclusions and serious-error rules; calculate totals in code and keep the PDF consistent with the underlying results.

- Store learner, agency, scenario, rubric and attempt records. Generate branded PDFs and an agreed basic export; preserve structured data for later reporting integrations.

- Implement agency and learner usage allowances, reset rules, alerts and limits as agreed. Handle simultaneous requests, retries and failed attempts without duplicate charging or results.

- Protect agency data boundaries, credentials and recordings. Apply agreed access, retention and deletion rules, with useful logs that do not expose unnecessary personal data.

- Deploy and maintain the application, manage environments and secrets, monitor latency and usage, resolve defects and hand over source code, configuration and operating documentation. 

Qualifications

Essential experience and skills

- Proven ownership of at least one working two-way voice application or conversational product with spoken interaction. Be ready to explain your contribution, architecture, latency, interruption handling, failure recovery and usage costs.

- Strong frontend development with TypeScript and React or a comparable framework; browser audio capture and playback, asynchronous UI behaviour, microphone permissions and session error states.

- Backend development in Python, for example FastAPI, or Node.js with TypeScript; REST APIs, WebSockets and/or WebRTC integration, authentication, background work and relational data modelling.

- Practical integration of LLM and speech services, using either real-time speech-to-speech or speech recognition, a language model and speech synthesis. Strength in one coherent stack is sufficient.

- Prompt and context design, structured model outputs, scenario grounding and evaluation. Ability to test responses against approved facts and recognise when the system should acknowledge missing information.

- Third-party API integration, secure session handling, SQL databases such as PostgreSQL, PDF generation and reliable export workflows.

- Automated testing and debugging across the browser, backend and AI services; Git, code review, deployment pipelines, Docker or equivalent packaging, and one cloud environment.

- Clear written English and the ability to translate a business requirement into a small, testable release, explaining assumptions and trade-offs to a non-technical project lead.

Preferred experience

Absorb or another 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; and integrations with Sheets, BigQuery, HubSpot or Zapier. Avatar integration is useful if later included in scope. These are advantages, not requirements to know every platform.

Additional Information

Role Details

Company & Location: Attain Solutions | Remote within India; Bengaluru preferred

Contract and capacity : Planned 8-12 weeks, full time at approximately 35-40 hours per week

Initial assessment: Paid 1-2 weeks; subsequent build work depends on the selected approach and project approval

Experience and start : Typically 5-8 years in software engineering; relevant delivery evidence takes priority. Near-term availability preferred.

Proposed duration and milestones : 

We recommend planning an initial 8-12-week engagement from kickoff. The paid assessment comes first. The remaining phases proceed against an agreed scope, estimate and project approval; their timing depends on the chosen route, content readiness and access.

Phase 1: Technical assessment

Duration : 1-2 weeks

Expected outcome : Options and reuse assessment; architecture; integration risks; work estimate; operating-cost assumptions; recommendation.

Phase 2: Voice prototype

Duration : 2 weeks

Expected outcome : A hosted two-way practice example and sample assessment on approved or clearly marked demonstration content; documented limitations.

Phase 3: First pilot release

Duration: 4-6 weeks

Expected outcome: Agreed personal/commercial pair, learner access, usage controls, scoring, coaching PDF, structured results and required integration.

Phase 4 : Validation and handover

Duration : 1-2 weeks

Expected outcome: User testing, scoring calibration with content specialists, defect fixes, deployment and documented handover.

This is a staffing allowance, not a committed production release date. A focused extension of an existing platform may need less time; additional integration or product scope must be estimated separately.

What successful delivery looks like

- The AI sustains the approved customer role across different learner approaches, raises the required practice opportunity and keeps scenario facts consistent.

- Representative strong, mixed and weak attempts are reviewed with the content specialists. Scores and feedback reflect demonstrated behaviour, with omissions and technical failures treated appropriately.

- Agreed browsers and LMS launch paths work. Access boundaries, usage limits, retries and common audio failures have been tested with Attain QA.

- Coaching PDFs match stored results. Actual audio measures are distinguished from text-derived estimates; optional speaking metrics are included only when agreed and validated.

- Source code, scenario and rubric configuration, deployment instructions, monitoring, cost assumptions and a support runbook are handed over.

Working arrangements and ongoing support

Provide a weekly demonstration, maintain an agreed task tracker and flag blockers early. Be available for scheduled US-time-zone discussions, with the overlap agreed in advance. Part-time support may continue for 3-6 months after the initial engagement, with scope and hours agreed separately; a starting planning allowance is 10-20 hours per month.

What to include when applying

Please share your CV or profile, earliest start date, weekly availability and expected hourly or monthly contract rate. Include a relevant voice-application demo or architecture walkthrough, your exact contribution, and one example of a difficult production issue you resolved. A degree in a relevant discipline or equivalent practical experience is suitable.

Selection will focus on a technical discussion and a walkthrough of relevant work. The selected engineer will begin with the paid assessment described above. Training content and grading standards will be supplied and approved by the client specialists; Attain will coordinate scope and QA support.

Terms

• Standard work timing: 3:00 PM to 12:00 AM IST, to ensure sufficient overlap with Tango Analytics' US-based teams and clients.
• Flexibility may be required during critical project milestones, deployment activities, go-live events, and production support periods.

• Location: Remote. Overlap with US morning and/or evening hours required.