3 Vector Embeddings Jobs

You will be responsible for designing, developing, and scaling the AI Agent Framework that powers automation-first modules in RevAi Pro, such as Tell Me, Action Center, and intelligent AI agents. This role is critical to shaping the core foundation of how automation, enterprise search, and just-in-time execution work inside our platform. Architect and implement the core orchestration engine for AI agents (event-driven/task-based). Manage agent lifecycle functions such as spawn, pause, escalate, and terminate. Enable secure, real-time communication between agents, services, and workflows. Integrate memory and retrieval systems using vector databases like Pinecone, Weaviate, or Qdrant. Integrate LLM providers (OpenAI, Azure OpenAI, Anthropic, Mistral, etc.) into agent workflows. Create modular prompt templates with retry/fallback mechanisms. Implement chaining logic and dynamic tool use for agents using LangChain or LlamaIndex. Develop reusable agent types such as Summarizer, Validator, Notifier, Planner, etc. Develop FastAPI-based microservices for agent orchestration and skill execution. Create APIs to register agents, execute agent actions, and manage runtime memory. Implement RBAC, rate limiting, and security protocols for multi-tenant deployments. Build connectors to integrate structured (CRM, SQL) and unstructured data sources (email, docs, transcripts). Route incoming data streams to relevant agents based on workflow and business rules. Support ingestion from tools like Salesforce, HubSpot, Gong, and Zoom. Deploy the agent platform using Docker and Kubernetes on Azure. Implement Redis, Celery, or equivalent async task systems for agent task queues. Set up observability to monitor agent usage, task success/failure, latency, and hallucination rates. Create CI/CD pipelines for agent modules and prompt updates. Ideal Candidate Profile: - 2-4 years of experience in backend engineering, ML engineering, or agent orchestration. - Strong command over Python (FastAPI, asyncio, Celery, SQLAlchemy). - Experience with LangChain, LlamaIndex, Haystack, or other orchestration libraries. - Hands-on with OpenAI, Anthropic, or similar LLM APIs. - Comfortable with vector embeddings and semantic search systems. - Understanding of modern AI agent frameworks like AutoGen, CrewAI, Semantic Planner, or ReAct. - Familiarity with multi-tenant API security and SaaS architecture. - Bonus: Frontend collaboration experience to support UI for agents and dashboards. - Bonus: Familiarity with SaaS platforms in B2B domains like RevOps, CRM, or workflow automation. What You'll Gain: - Ownership of agent architecture inside a live enterprise-grade AI platform. - Opportunity to shape the future of AI-first business applications. - Collaboration with founders, product leaders, and early enterprise customers. - Competitive salary with potential ESOP. - First-mover engineering credit on one of the most advanced automation stacks in SaaS.,

As a skilled professional in the field of Conversational Text AI Platform, your primary responsibility will be to develop and maintain state-of-the-art Conversational Text AI systems using cutting-edge LLM frameworks. You will collaborate closely with product owners and domain experts to create reusable components tailored to specific business processes. Additionally, you will be tasked with building core infrastructure and reusable components that facilitate the seamless deployment of conversational AI systems. Your expertise will be crucial in working on orchestration, prompt engineering, and LLM-powered integrations, ensuring the scalability and integration of solutions with enterprise data platforms. In the realm of Generative AI & Model Optimization, you will be expected to fine-tune LLMs/SLMs using proprietary NBFC data and perform distillation and quantization of models for edge deployment. Your role will involve evaluating and running LLM/SLM models on local/edge server machines, contributing to the optimization and efficiency of the AI models. Moreover, you will play a key role in developing self-learning frameworks that allow systems to adapt without complete retraining, incorporating lightweight local models for real-time learning on the edge. Your expertise will be crucial in enhancing the adaptability and learning capabilities of AI systems. The ideal candidate for this role should possess a Bachelor's or Master's degree in Computer Science, Engineering, or a related field, along with at least 7 years of experience in Python, Node.JS, JavaScript, HTML/CSS, Redis, Postgres, Azure COSMOS, DevOps, and CI/CD, with exposure to AI/ML technologies. Strong programming skills in languages like Python, Node.JS, and JavaScript are essential, along with familiarity with Redis, Postgres, Vector Embeddings, Speech-to-Text & Text-to-Speech Services, Azure COSMOS, DevOps, and CI/CD practices. Experience in building or integrating LLMs for task automation, reasoning, or autonomous workflows, as well as a solid understanding of prompt engineering, tool calling, and agent orchestration, will be highly valued. Joining our team at Bajaj Finance Limited offers you the opportunity to be part of a dynamic and diverse organization that values its people and fosters a culture of innovation and achievement. With over 500 locations across India, we provide a stimulating work environment where your skills and drive can lead to rewarding accomplishments. This is a full-time position that requires in-person work at the designated location.,

As a member of our team, you will be responsible for working on the Conversational Text AI Platform, where your primary tasks will include building and maintaining the system using cutting-edge LLM frameworks. You will collaborate closely with product owners and domain experts to develop reusable components for various business processes. Additionally, you will play a key role in developing core infrastructure and reusable components to facilitate the deployment of conversational AI systems. Your work will involve orchestration, prompt engineering, and integrating LLM-powered solutions with enterprise data platforms. In the realm of Generative AI & Model Optimization, you will be engaged in fine-tuning LLMs/SLMs using proprietary NBFC data, as well as performing distillation and quantization of models for edge deployment. Your responsibilities will also include evaluating and running LLM/SLM models on local/edge server machines. Furthermore, you will have the opportunity to build self-learning systems that can adapt without requiring full retraining, enabling real-time learning on the edge through lightweight local models. The ideal candidate for this role will possess a Bachelor's or Master's degree in computer science, engineering, or a related field, along with a minimum of 7 years of experience in Python, Node.JS, JavaScript, HTML/CSS, Redis, Postgres, Azure COSMOS, DevOps, and CI/CD, with exposure to AI/ML. Strong programming skills in Python, Node.JS, JavaScript, and HTML/CSS are essential, along with familiarity with Redis, Postgres, Vector Embeddings, Speech-to-Text & Text-to-Speech Services, Azure COSMOS, DevOps, CI/CD, Lang-Chain, or Lang-Graph. Experience in building or integrating LLMs for task automation, reasoning, or autonomous workflows, as well as a solid understanding of prompt engineering, tool calling, and agent orchestration, will be highly valued.,