Artificial Intelligence Engineer

LOGZ; Chennai; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

LOGZ is hiring AI Engineers to build internal AI products and to integrate AI into our existing software stack. You will work on voice AI, LLM-powered tools, and agents that act inside our systems.

This role emphasizes practical AI outcomes over theoretical work, with an emphasis on shipping usable features. Responsibilities include end-to-end development from prototype to production, strong backend and frontend work, and choosing models based on quality, latency, and cost.

Qualifications

• 1–2 years of professional software or AI engineering.
• Hands-on LLM work: prompting, function/tool calling, RAG.
• Backend: Python and/or Node.js, REST APIs, async jobs, Postgres or similar.
• Frontend: React or similar, enough to build internal tools and product screens.
• Git, Linux, Docker, and third-party AI APIs (OpenAI, AWS, or self-hosted models).
• AWS: Working knowledge of AWS services you have actually used.

Responsibilities

• Notetaker: Build internal AI tools to capture audio, transcribe, summarize, extract actions, and be searchable.
• Voice AI: Develop STT, TTS, diarization, and pipelines.
• LLMs and agents: Design and ship RAG, tool-calling agents, workflows.
• Product integration: Integrate AI into existing APIs and internal services.
• Full stack: Own backend endpoints, data stores, background jobs, and frontend for internal tools.
• Model choice: Compare hosted vs open-source models for quality, latency, cost.
• Quality and safety: Logging, evals, fallbacks, access control.

Skills

Python

Node.js

React

REST APIs

Git

Linux

Docker

AWS

LLMs

Education

Bachelor's degree in Computer Science

Tools

PostgreSQL

Docker

AWS

OpenAI API

LangChain

LlamaIndex

Job description

We are hiring AI Engineers to build internal AI products and to add AI into existing company software. Work includes voice AI (meeting notetaker, transcription, summaries), LLM-based tools, and agents that take actions inside our systems.

You will ship end-to-end: prototype, APIs, a usable UI, and production-ready features. Strongest skill should be applied AI. Backend and frontend need to be solid enough to build and ship, not specialist-level.

Role: AI Engineer. Experience: 1-2 years. Location: India. Employment type: Full-time.

What you will do:

• Notetaker: Build internal AI tools such as a meeting notetaker: capture audio, transcribe, summarize, extract action items, and make them searchable.


• Voice AI: Work with speech and voice models: STT, TTS, speaker diarization, batch and near-real-time pipelines.


• LLMs and agents: Design and ship LLM features: RAG, tool-calling agents, structured extraction, and multi-step workflows.


• Product integration: Integrate AI into existing APIs, web apps, and internal services (assistants, automations, copilots).


• Full stack: Own simple full-stack slices: backend endpoints, data stores, background jobs, and a clean frontend for internal tools and product UI.


• Model choice: Compare models and vendors (hosted APIs vs open-source), and choose based on quality, latency, and cost.


• Quality and safety: Add logging, basic evals, fallbacks, and practical safety (PII, wrong answers, access control).


• Delivery: Turn a vague product idea into a scoped MVP, then harden it for real use.


• Cloud: Build and run these systems on AWS.

What you need to know:

Must have:

• Experience: 1-2 years of professional software or AI engineering. Strong internships or real shipped projects count.


• LLMs: Hands-on LLM work: prompting, function/tool calling, RAG, embeddings. LangChain / LlamaIndex or equivalent custom pipelines.


• Voice: Practical speech/voice experience, or a clear ability to get there quickly (Whisper or similar STT, audio pipelines).


• Backend: Python and/or Node.js, REST APIs, async jobs, Postgres or similar.


• Frontend: React or similar, enough to build internal tools and product screens.


• Tooling: Git, Linux, Docker, and third-party AI APIs (OpenAI, AWS, or self-hosted models).


• AWS: Working knowledge of AWS (for example S3, Lambda, EC2, ECS, SQS, or equivalent services you have actually used).


• Communication: Clear written English. Able to scope and ship without a fully written spec.

Nice-to-haves:

• Real-time voice (WebRTC, websocket audio, live captions).


• Agents that call tools and write back to systems, not chat-only demos.


• Vector databases (pgvector, Pinecone, Qdrant, or similar).


• FastAPI / Express / Nest, websockets, background workers.


• Prompt versioning, eval harnesses, cost/latency tracking.


• Deeper AWS experience (Bedrock, Transcribe, SageMaker, IAM, CloudWatch).

Education:

Bachelor's degree in Computer Science or a related field.