AI Engineer

ConnexR Solutions Pvt Ltd; Bengaluru; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

ConnexR Solutions Pvt Ltd in Bengaluru is seeking experienced software engineers to build and productionize RAG-based chatbots and AI assistants. You will integrate LLMs, embedding models, vector databases, and cloud AI services, while developing speech-to-text and text-to-speech solutions.

Collaboration with cross-functional teams is essential to ensure scalable AI products. Ideal candidates have hands-on Python, strong AI/ML fundamentals, and experience with streaming, evaluation, and

Qualifications

• Strong Python programming and software engineering fundamentals, including testing, version control, code reviews, and API design.
• Hands-on experience with LLMs and frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
• End-to-end RAG development, including vector databases and embedding models.
• Experience with cloud AI platforms such as Azure OpenAI, AWS Bedrock, Google Vertex AI, or Databricks.
• Experience with speech technologies such as Whisper, Azure Speech, Google STT/TTS, or ElevenLabs.
• LLM evaluation, quality assessment, and systematic debugging.
• Docker, Kubernetes or serverless deployment, and CI/CD pipelines.
• Excellent communication skills and the ability to explain technical concepts and trade-offs to non-technical stakeholders.

Responsibilities

• Build and productionize RAG-based chatbots and AI assistants.
• Integrate LLMs, embedding models, vector databases, and cloud AI services.
• Develop speech-to-text and text-to-speech solutions.
• Evaluate model performance and troubleshoot AI quality issues.
• Deploy, monitor, and maintain scalable AI applications.
• Collaborate with product, infrastructure, business, and compliance teams.

Skills

Python programming

Testing

Version control

Code reviews

API design

LangChain

LlamaIndex

Semantic Kernel

RAG development

Vector databases

Embedding models

Azure OpenAI

AWS Bedrock

Vertex AI

Databricks

Whisper

Azure Speech

Google STT/TTS

ElevenLabs

LLM evaluation

Quality assessment

Debugging

Docker

Kubernetes

Serverless

CI/CD

Communication

Video models

FFmpeg

Lip-sync

Subtitle generation

Fine-tuning

LoRA/PEFT

Model distillation

Real-time audio streaming

Low-latency voice agents

React/TypeScript

Localization

GDPR knowledge

EU AI Act knowledge

GxP knowledge

MLflow

LangSmith

Weights & Biases

Tools

Docker

Kubernetes

Job description

Experience: 4+ years in software engineering, including 2+ years building AI/ML-powered products

Work Mode: Onsite

Employment Type: Full-Time

Shift: Rotational

Notice Period: To be confirmed

Interview Process: 3 technical rounds via video

Mandatory Skills

Strong Python programming and software engineering fundamentals, including testing, version control, code reviews, and API design.

Hands-on experience with LLMs and frameworks such as LangChain, LlamaIndex, or Semantic Kernel.

End-to-end RAG development, including vector databases and embedding models.

Experience with cloud AI platforms such as Azure OpenAI, AWS Bedrock, Google Vertex AI, or Databricks.

Experience with speech technologies such as Whisper, Azure Speech, Google STT/TTS, or ElevenLabs.

LLM evaluation, quality assessment, and systematic debugging.

Docker, Kubernetes or serverless deployment, and CI/CD pipelines.

Excellent communication skills and the ability to explain technical concepts and trade-offs to non-technical stakeholders.

Good to Have

Generative video models such as Veo, Sora, Runway, or Pika.

Media processing using FFmpeg, lip-sync, and subtitle generation.

Fine-tuning, LoRA/PEFT, or model distillation.

Real-time audio streaming and low-latency voice agents.

React/TypeScript, multilingual AI solutions, and localization.

GDPR, EU AI Act, or GxP knowledge.

MLOps/LLMOps tools such as MLflow, LangSmith, or Weights & Biases.

Role Responsibilities

Build and productionize RAG-based chatbots and AI assistants.

Integrate LLMs, embedding models, vector databases, and cloud AI services.

Develop speech-to-text and text-to-speech solutions.

Evaluate model performance and troubleshoot AI quality issues.

Deploy, monitor, and maintain scalable AI applications.

Collaborate with product, infrastructure, business, and compliance teams.

Interested candidates must have strong hands-on Python, LLM, RAG, cloud AI, and speech technology experience. Excellent communication skills are essential.