Location: Hyderabad, India

Work type: On-site / Work from Office

About Us

We’re building a conversational voice assistant. Join early to shape core services, data models, and our AI/LLM platform.

The road ahead: We’re scaling to thousands of concurrent calls, maturing an AWS-native platform (secure, observable, cost-aware). You’ll help evolve our LLM/RAG stack, deploy reliable pipelines, and set engineering standards.

What You’ll Do

• Design and own Python/FastAPI microservices (async I/O, WebSockets) for real-time voice/data workflows.
• Model and operate MongoDB/Atlas: schema design, indexing, aggregation pipelines, query tuning, TTL/archival, change streams.
• Integrate third-party APIs/services (auth, webhooks, retries, idempotency, observability) and productionize them.
• Contribute to LLM features: tool/function calling, structured outputs (Pydantic/JSON Schema), RAG , evaluations, safety/guardrails.
• Create and maintain deployment pipelines; add metrics, logs, and traces; drive incident response and postmortems.
• Collaborate with frontend/AI/QA; write docs/runbooks; communicate clearly and work as a supportive team member.

Must-Haves

• ‍3+ years backend experience with Python (strong) and FastAPI (or similar async frameworks).
• MongoDB proficiency: schema design, indexes, aggregation, profiling, performance tuning; operational know-how on Atlas.
• CI/CD (GitHub Actions/GitLab CI or similar) and Docker.
• Strong debugging across distributed systems; excellent communication and teamwork.
• Proven third-party integration experience (auth, rate limits, pagination, webhooks).

LLM / AI Experience (Preferred/Plus)

• Server-side integration with providers (e.g., OpenAI/Azure OpenAI/Bedrock) and streaming responses.
• RAG pipelines (chunking, embeddings, vector stores), prompt versioning, structured outputs.
• Evaluation & safety basics (offline eval sets, regression tests, guardrails/PHI redaction, latency & cost tracking).

Nice-to-Haves

• Node.js/TypeScript for tools/edge services.
• PostgreSQL/Redis; event/messaging (Kafka/Kinesis/RabbitMQ).
• Real-time comms (SIP/WebRTC), audio streaming, STT/TTS.
• Security/compliance awareness (SOC 2, HIPAA), secrets management.
• Hands-on AWS: IAM & VPC basics, S3, SQS/SNS, API Gateway/ALB, CloudWatch; deploy via ECR + ECS/EKS or Lambda.

Why Join

• ‍Real impact, real users: Ship services that power sensitive workflows and live phone calls, your work goes into production and gets used every day.
• ‍Ownership from day 1: Design → build → deploy → monitor your services. No heavy bureaucracy; you’ll make architectural decisions that stick.
• ‍Deep technical growth: Work across Python/FastAPI, AWS (ECS/EKS/Lambda, S3, SQS/SNS, CloudWatch), MongoDB/Atlas and LLM/RAG pipelines, tool calling, and structured outputs.
• ‍Hard, meaningful problems: Low-latency real-time pipelines (WebSockets/audio), reliability at scale, cost/latency tuning, and robust observability.
• ‍Fast feedback loop: Automated CI/CD, frequent releases, data-driven decisions, clear success metrics (latency, reliability, cost).
• ‍Strong engineering culture: Thoughtful code reviews, postmortems, runbooks, and documentation supportive teammates who communicate clearly.
• ‍Mission + rigor: Build SOC2/HIPAA-aligned systems that genuinely help users while meeting high security and privacy bars.
• ‍Career acceleration: Grow into a domain owner/tech lead within 6–12 months by consistently delivering and raising the quality bar.
• ‍Remote-friendly & collaborative: Pragmatic processes, respectful schedules, and a focus on outcomes over hours.

‍

Let's talk at careers@interactly.ai